Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/QwQ-32B-Preview
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) on the Sky-T1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9858605558264264,
+    "total_flos": 1495659198021632.0,
+    "train_loss": 0.09055571391740266,
+    "train_runtime": 153095.38,
+    "train_samples_per_second": 0.321,
+    "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/QwQ-32B-Preview",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6bc9a94872a4a63a8891ea7aae4128685bdb385bf62652cde5c7a4172f4c6e
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3b3df33e82087a07dcbc77bdc6976da8c945a4f8ee626269d0ebc6b4fb7341
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c295a4d6cd4df5b1698ea78d7aec645b9109c12d7aee1544f7f2debf2a2d3d8e
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af31acd7d76e097add3aef36b09105c21aeb371bba655fc1439cf3adf4c3cabb
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1c151ec8cd9e257bad81cace006048ca34cb331880827cf9005f23debee432
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8013e4ea16c0fc5ff3c24fadd1888897a61439f9b8c564ee22c86d982d7b0d
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e2c9fe2ccd113286433bc168274325ac46b5ac39fd0af751a7fe3ee5b3e146
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa47e83cde2d0fa2a3180957b95297ec3ee3d05cb4079476da86565e8d90bdd8
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e42dda50337d200844d5f5ee9a3f052d7d15a91f4506d4c383945bdb4799510
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a2d49ed8f02a9a05e3eb99fd09e1f2d6f3a4e40fbebc3eb32f189f8751eee7
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82b6509d5a453f330549e16ad8ab0b82c871d8172f1e30598a9a2f2cf7abb802
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e516c1be6927109e74f07e84ebafe8608a32f0fba80d55f9466efd17a13424
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601d19dfd8bb3c500412c45d442fb21e3ce902307eae35ab31d5b84cef817497
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd264904eadbaa19b525765e0bf55dd36d511400959a69ec1fb433b8e3b0e6aa
+size 2123397800

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"
+  }
+}

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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        {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|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) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.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' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9858605558264264,
+    "total_flos": 1495659198021632.0,
+    "train_loss": 0.09055571391740266,
+    "train_runtime": 153095.38,
+    "train_samples_per_second": 0.321,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,3612 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9858605558264264,
+  "eval_steps": 500,
+  "global_step": 510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005850804485616773,
+      "grad_norm": 6.383665084838867,
+      "learning_rate": 1.9607843137254904e-07,
+      "loss": 0.207,
+      "step": 1
+    },
+    {
+      "epoch": 0.011701608971233545,
+      "grad_norm": 6.675337314605713,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 0.2143,
+      "step": 2
+    },
+    {
+      "epoch": 0.017552413456850317,
+      "grad_norm": 7.4617815017700195,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.2293,
+      "step": 3
+    },
+    {
+      "epoch": 0.02340321794246709,
+      "grad_norm": 5.585313320159912,
+      "learning_rate": 7.843137254901962e-07,
+      "loss": 0.1861,
+      "step": 4
+    },
+    {
+      "epoch": 0.02925402242808386,
+      "grad_norm": 5.630923748016357,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.1921,
+      "step": 5
+    },
+    {
+      "epoch": 0.035104826913700635,
+      "grad_norm": 5.787583827972412,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.1962,
+      "step": 6
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 5.5350823402404785,
+      "learning_rate": 1.3725490196078434e-06,
+      "loss": 0.1839,
+      "step": 7
+    },
+    {
+      "epoch": 0.04680643588493418,
+      "grad_norm": 5.308877944946289,
+      "learning_rate": 1.5686274509803923e-06,
+      "loss": 0.1818,
+      "step": 8
+    },
+    {
+      "epoch": 0.05265724037055095,
+      "grad_norm": 6.017881393432617,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.2044,
+      "step": 9
+    },
+    {
+      "epoch": 0.05850804485616772,
+      "grad_norm": 3.9479219913482666,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.1677,
+      "step": 10
+    },
+    {
+      "epoch": 0.0643588493417845,
+      "grad_norm": 3.2280476093292236,
+      "learning_rate": 2.1568627450980393e-06,
+      "loss": 0.1684,
+      "step": 11
+    },
+    {
+      "epoch": 0.07020965382740127,
+      "grad_norm": 3.0776169300079346,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.1723,
+      "step": 12
+    },
+    {
+      "epoch": 0.07606045831301804,
+      "grad_norm": 1.9993395805358887,
+      "learning_rate": 2.549019607843137e-06,
+      "loss": 0.159,
+      "step": 13
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 2.2911689281463623,
+      "learning_rate": 2.7450980392156867e-06,
+      "loss": 0.1769,
+      "step": 14
+    },
+    {
+      "epoch": 0.08776206728425158,
+      "grad_norm": 2.2151801586151123,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.1598,
+      "step": 15
+    },
+    {
+      "epoch": 0.09361287176986836,
+      "grad_norm": 2.7120745182037354,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 0.1625,
+      "step": 16
+    },
+    {
+      "epoch": 0.09946367625548513,
+      "grad_norm": 2.8011069297790527,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1803,
+      "step": 17
+    },
+    {
+      "epoch": 0.1053144807411019,
+      "grad_norm": 2.3757805824279785,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.1696,
+      "step": 18
+    },
+    {
+      "epoch": 0.11116528522671867,
+      "grad_norm": 2.58486270904541,
+      "learning_rate": 3.7254901960784316e-06,
+      "loss": 0.1831,
+      "step": 19
+    },
+    {
+      "epoch": 0.11701608971233544,
+      "grad_norm": 2.677863121032715,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 0.1519,
+      "step": 20
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 2.3059568405151367,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.1609,
+      "step": 21
+    },
+    {
+      "epoch": 0.128717698683569,
+      "grad_norm": 1.1877626180648804,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 0.155,
+      "step": 22
+    },
+    {
+      "epoch": 0.13456850316918575,
+      "grad_norm": 0.8065866827964783,
+      "learning_rate": 4.509803921568628e-06,
+      "loss": 0.1608,
+      "step": 23
+    },
+    {
+      "epoch": 0.14041930765480254,
+      "grad_norm": 0.7501436471939087,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.1692,
+      "step": 24
+    },
+    {
+      "epoch": 0.1462701121404193,
+      "grad_norm": 0.659354031085968,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 0.1455,
+      "step": 25
+    },
+    {
+      "epoch": 0.15212091662603608,
+      "grad_norm": 0.6396603584289551,
+      "learning_rate": 5.098039215686274e-06,
+      "loss": 0.1498,
+      "step": 26
+    },
+    {
+      "epoch": 0.15797172111165286,
+      "grad_norm": 0.8220036029815674,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.1449,
+      "step": 27
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.7791479229927063,
+      "learning_rate": 5.4901960784313735e-06,
+      "loss": 0.1428,
+      "step": 28
+    },
+    {
+      "epoch": 0.1696733300828864,
+      "grad_norm": 0.9419583678245544,
+      "learning_rate": 5.686274509803922e-06,
+      "loss": 0.1395,
+      "step": 29
+    },
+    {
+      "epoch": 0.17552413456850316,
+      "grad_norm": 0.7534624934196472,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.1439,
+      "step": 30
+    },
+    {
+      "epoch": 0.18137493905411994,
+      "grad_norm": 0.6648500561714172,
+      "learning_rate": 6.07843137254902e-06,
+      "loss": 0.1391,
+      "step": 31
+    },
+    {
+      "epoch": 0.18722574353973673,
+      "grad_norm": 0.7320256233215332,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 0.1461,
+      "step": 32
+    },
+    {
+      "epoch": 0.19307654802535348,
+      "grad_norm": 0.5900516510009766,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.1504,
+      "step": 33
+    },
+    {
+      "epoch": 0.19892735251097027,
+      "grad_norm": 0.5753044486045837,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1406,
+      "step": 34
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.5507317185401917,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.1313,
+      "step": 35
+    },
+    {
+      "epoch": 0.2106289614822038,
+      "grad_norm": 0.6329162120819092,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.1462,
+      "step": 36
+    },
+    {
+      "epoch": 0.21647976596782056,
+      "grad_norm": 0.5627315640449524,
+      "learning_rate": 7.2549019607843145e-06,
+      "loss": 0.1526,
+      "step": 37
+    },
+    {
+      "epoch": 0.22233057045343735,
+      "grad_norm": 0.5392419099807739,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 0.1144,
+      "step": 38
+    },
+    {
+      "epoch": 0.22818137493905413,
+      "grad_norm": 0.6186360716819763,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.1379,
+      "step": 39
+    },
+    {
+      "epoch": 0.2340321794246709,
+      "grad_norm": 0.5838163495063782,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.1477,
+      "step": 40
+    },
+    {
+      "epoch": 0.23988298391028767,
+      "grad_norm": 0.6214900612831116,
+      "learning_rate": 8.03921568627451e-06,
+      "loss": 0.1244,
+      "step": 41
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.7451300621032715,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.1501,
+      "step": 42
+    },
+    {
+      "epoch": 0.2515845928815212,
+      "grad_norm": 0.6587160229682922,
+      "learning_rate": 8.43137254901961e-06,
+      "loss": 0.1381,
+      "step": 43
+    },
+    {
+      "epoch": 0.257435397367138,
+      "grad_norm": 0.5924107432365417,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 0.1356,
+      "step": 44
+    },
+    {
+      "epoch": 0.26328620185275475,
+      "grad_norm": 0.5446859002113342,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.1204,
+      "step": 45
+    },
+    {
+      "epoch": 0.2691370063383715,
+      "grad_norm": 0.5046283602714539,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 0.1333,
+      "step": 46
+    },
+    {
+      "epoch": 0.2749878108239883,
+      "grad_norm": 0.4857878088951111,
+      "learning_rate": 9.215686274509804e-06,
+      "loss": 0.1307,
+      "step": 47
+    },
+    {
+      "epoch": 0.2808386153096051,
+      "grad_norm": 0.5312994718551636,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.1275,
+      "step": 48
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.5524762272834778,
+      "learning_rate": 9.607843137254903e-06,
+      "loss": 0.1366,
+      "step": 49
+    },
+    {
+      "epoch": 0.2925402242808386,
+      "grad_norm": 0.5190322399139404,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.1419,
+      "step": 50
+    },
+    {
+      "epoch": 0.2983910287664554,
+      "grad_norm": 0.46393024921417236,
+      "learning_rate": 1e-05,
+      "loss": 0.1392,
+      "step": 51
+    },
+    {
+      "epoch": 0.30424183325207216,
+      "grad_norm": 0.4669331908226013,
+      "learning_rate": 9.999882884955554e-06,
+      "loss": 0.117,
+      "step": 52
+    },
+    {
+      "epoch": 0.3100926377376889,
+      "grad_norm": 0.49370425939559937,
+      "learning_rate": 9.999531545308584e-06,
+      "loss": 0.1359,
+      "step": 53
+    },
+    {
+      "epoch": 0.3159434422233057,
+      "grad_norm": 0.4881090223789215,
+      "learning_rate": 9.998945997517957e-06,
+      "loss": 0.1303,
+      "step": 54
+    },
+    {
+      "epoch": 0.3217942467089225,
+      "grad_norm": 0.5082895755767822,
+      "learning_rate": 9.998126269014255e-06,
+      "loss": 0.1311,
+      "step": 55
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.4817737936973572,
+      "learning_rate": 9.997072398198492e-06,
+      "loss": 0.1341,
+      "step": 56
+    },
+    {
+      "epoch": 0.333495855680156,
+      "grad_norm": 0.49731704592704773,
+      "learning_rate": 9.99578443444032e-06,
+      "loss": 0.1258,
+      "step": 57
+    },
+    {
+      "epoch": 0.3393466601657728,
+      "grad_norm": 0.4882417321205139,
+      "learning_rate": 9.994262438075713e-06,
+      "loss": 0.1479,
+      "step": 58
+    },
+    {
+      "epoch": 0.34519746465138956,
+      "grad_norm": 0.47016623616218567,
+      "learning_rate": 9.992506480404137e-06,
+      "loss": 0.1333,
+      "step": 59
+    },
+    {
+      "epoch": 0.3510482691370063,
+      "grad_norm": 0.4617152214050293,
+      "learning_rate": 9.990516643685222e-06,
+      "loss": 0.134,
+      "step": 60
+    },
+    {
+      "epoch": 0.35689907362262313,
+      "grad_norm": 0.4279603064060211,
+      "learning_rate": 9.988293021134888e-06,
+      "loss": 0.1259,
+      "step": 61
+    },
+    {
+      "epoch": 0.3627498781082399,
+      "grad_norm": 0.4004892408847809,
+      "learning_rate": 9.985835716921e-06,
+      "loss": 0.1313,
+      "step": 62
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.49121877551078796,
+      "learning_rate": 9.983144846158472e-06,
+      "loss": 0.1376,
+      "step": 63
+    },
+    {
+      "epoch": 0.37445148707947346,
+      "grad_norm": 0.543146550655365,
+      "learning_rate": 9.980220534903889e-06,
+      "loss": 0.1358,
+      "step": 64
+    },
+    {
+      "epoch": 0.3803022915650902,
+      "grad_norm": 0.4203166365623474,
+      "learning_rate": 9.977062920149583e-06,
+      "loss": 0.1415,
+      "step": 65
+    },
+    {
+      "epoch": 0.38615309605070697,
+      "grad_norm": 0.5869492888450623,
+      "learning_rate": 9.973672149817232e-06,
+      "loss": 0.1245,
+      "step": 66
+    },
+    {
+      "epoch": 0.3920039005363237,
+      "grad_norm": 0.38548362255096436,
+      "learning_rate": 9.970048382750925e-06,
+      "loss": 0.1349,
+      "step": 67
+    },
+    {
+      "epoch": 0.39785470502194054,
+      "grad_norm": 0.43501177430152893,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.1372,
+      "step": 68
+    },
+    {
+      "epoch": 0.4037055095075573,
+      "grad_norm": 0.459250807762146,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 0.1482,
+      "step": 69
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.4854992926120758,
+      "learning_rate": 9.957780853265441e-06,
+      "loss": 0.139,
+      "step": 70
+    },
+    {
+      "epoch": 0.41540711847879086,
+      "grad_norm": 0.4333488941192627,
+      "learning_rate": 9.953226905881208e-06,
+      "loss": 0.1181,
+      "step": 71
+    },
+    {
+      "epoch": 0.4212579229644076,
+      "grad_norm": 0.43450847268104553,
+      "learning_rate": 9.948440919541277e-06,
+      "loss": 0.1328,
+      "step": 72
+    },
+    {
+      "epoch": 0.4271087274500244,
+      "grad_norm": 0.4384412467479706,
+      "learning_rate": 9.943423118450051e-06,
+      "loss": 0.1405,
+      "step": 73
+    },
+    {
+      "epoch": 0.43295953193564113,
+      "grad_norm": 0.5065910816192627,
+      "learning_rate": 9.938173737671531e-06,
+      "loss": 0.1416,
+      "step": 74
+    },
+    {
+      "epoch": 0.43881033642125794,
+      "grad_norm": 0.48674866557121277,
+      "learning_rate": 9.932693023118299e-06,
+      "loss": 0.1432,
+      "step": 75
+    },
+    {
+      "epoch": 0.4446611409068747,
+      "grad_norm": 0.47392505407333374,
+      "learning_rate": 9.926981231540007e-06,
+      "loss": 0.1468,
+      "step": 76
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.43997856974601746,
+      "learning_rate": 9.921038630511345e-06,
+      "loss": 0.1523,
+      "step": 77
+    },
+    {
+      "epoch": 0.45636274987810826,
+      "grad_norm": 0.42127934098243713,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.1443,
+      "step": 78
+    },
+    {
+      "epoch": 0.462213554363725,
+      "grad_norm": 0.43109971284866333,
+      "learning_rate": 9.908462124451152e-06,
+      "loss": 0.1401,
+      "step": 79
+    },
+    {
+      "epoch": 0.4680643588493418,
+      "grad_norm": 0.45185860991477966,
+      "learning_rate": 9.901828808578846e-06,
+      "loss": 0.1203,
+      "step": 80
+    },
+    {
+      "epoch": 0.47391516333495853,
+      "grad_norm": 0.43880337476730347,
+      "learning_rate": 9.894965861547023e-06,
+      "loss": 0.1331,
+      "step": 81
+    },
+    {
+      "epoch": 0.47976596782057535,
+      "grad_norm": 0.45226937532424927,
+      "learning_rate": 9.887873604857424e-06,
+      "loss": 0.1374,
+      "step": 82
+    },
+    {
+      "epoch": 0.4856167723061921,
+      "grad_norm": 0.4365948438644409,
+      "learning_rate": 9.88055237075403e-06,
+      "loss": 0.1412,
+      "step": 83
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.43214043974876404,
+      "learning_rate": 9.873002502207502e-06,
+      "loss": 0.1441,
+      "step": 84
+    },
+    {
+      "epoch": 0.49731838127742567,
+      "grad_norm": 0.4197068214416504,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.149,
+      "step": 85
+    },
+    {
+      "epoch": 0.5031691857630424,
+      "grad_norm": 0.41914910078048706,
+      "learning_rate": 9.857218287204204e-06,
+      "loss": 0.1285,
+      "step": 86
+    },
+    {
+      "epoch": 0.5090199902486592,
+      "grad_norm": 0.4386901259422302,
+      "learning_rate": 9.848984680175049e-06,
+      "loss": 0.1459,
+      "step": 87
+    },
+    {
+      "epoch": 0.514870794734276,
+      "grad_norm": 0.39859330654144287,
+      "learning_rate": 9.840523917523354e-06,
+      "loss": 0.146,
+      "step": 88
+    },
+    {
+      "epoch": 0.5207215992198927,
+      "grad_norm": 0.4264526665210724,
+      "learning_rate": 9.831836395602164e-06,
+      "loss": 0.1254,
+      "step": 89
+    },
+    {
+      "epoch": 0.5265724037055095,
+      "grad_norm": 0.4199821352958679,
+      "learning_rate": 9.822922521387277e-06,
+      "loss": 0.1376,
+      "step": 90
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.41378048062324524,
+      "learning_rate": 9.813782712458206e-06,
+      "loss": 0.1306,
+      "step": 91
+    },
+    {
+      "epoch": 0.538274012676743,
+      "grad_norm": 0.4491420090198517,
+      "learning_rate": 9.804417396978605e-06,
+      "loss": 0.1333,
+      "step": 92
+    },
+    {
+      "epoch": 0.5441248171623598,
+      "grad_norm": 0.48420554399490356,
+      "learning_rate": 9.794827013676206e-06,
+      "loss": 0.152,
+      "step": 93
+    },
+    {
+      "epoch": 0.5499756216479766,
+      "grad_norm": 0.43099677562713623,
+      "learning_rate": 9.78501201182228e-06,
+      "loss": 0.1477,
+      "step": 94
+    },
+    {
+      "epoch": 0.5558264261335933,
+      "grad_norm": 0.44019651412963867,
+      "learning_rate": 9.774972851210572e-06,
+      "loss": 0.1388,
+      "step": 95
+    },
+    {
+      "epoch": 0.5616772306192102,
+      "grad_norm": 0.4409557580947876,
+      "learning_rate": 9.764710002135784e-06,
+      "loss": 0.1262,
+      "step": 96
+    },
+    {
+      "epoch": 0.567528035104827,
+      "grad_norm": 0.4218440353870392,
+      "learning_rate": 9.754223945371524e-06,
+      "loss": 0.1397,
+      "step": 97
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.400522917509079,
+      "learning_rate": 9.743515172147793e-06,
+      "loss": 0.1317,
+      "step": 98
+    },
+    {
+      "epoch": 0.5792296440760605,
+      "grad_norm": 0.41842326521873474,
+      "learning_rate": 9.732584184127973e-06,
+      "loss": 0.1391,
+      "step": 99
+    },
+    {
+      "epoch": 0.5850804485616772,
+      "grad_norm": 0.3865659236907959,
+      "learning_rate": 9.721431493385322e-06,
+      "loss": 0.1281,
+      "step": 100
+    },
+    {
+      "epoch": 0.590931253047294,
+      "grad_norm": 0.38467201590538025,
+      "learning_rate": 9.710057622378992e-06,
+      "loss": 0.1359,
+      "step": 101
+    },
+    {
+      "epoch": 0.5967820575329108,
+      "grad_norm": 0.4947831630706787,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.1451,
+      "step": 102
+    },
+    {
+      "epoch": 0.6026328620185275,
+      "grad_norm": 0.4190811514854431,
+      "learning_rate": 9.686648481193994e-06,
+      "loss": 0.1432,
+      "step": 103
+    },
+    {
+      "epoch": 0.6084836665041443,
+      "grad_norm": 0.38624292612075806,
+      "learning_rate": 9.674614307640368e-06,
+      "loss": 0.1352,
+      "step": 104
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.43240782618522644,
+      "learning_rate": 9.66236114702178e-06,
+      "loss": 0.1422,
+      "step": 105
+    },
+    {
+      "epoch": 0.6201852754753778,
+      "grad_norm": 0.4440532326698303,
+      "learning_rate": 9.649889573350006e-06,
+      "loss": 0.135,
+      "step": 106
+    },
+    {
+      "epoch": 0.6260360799609946,
+      "grad_norm": 0.39602479338645935,
+      "learning_rate": 9.637200170868607e-06,
+      "loss": 0.1186,
+      "step": 107
+    },
+    {
+      "epoch": 0.6318868844466115,
+      "grad_norm": 0.4450910687446594,
+      "learning_rate": 9.62429353402556e-06,
+      "loss": 0.1344,
+      "step": 108
+    },
+    {
+      "epoch": 0.6377376889322282,
+      "grad_norm": 0.4157448410987854,
+      "learning_rate": 9.611170267445401e-06,
+      "loss": 0.1382,
+      "step": 109
+    },
+    {
+      "epoch": 0.643588493417845,
+      "grad_norm": 0.43927744030952454,
+      "learning_rate": 9.597830985900913e-06,
+      "loss": 0.132,
+      "step": 110
+    },
+    {
+      "epoch": 0.6494392979034618,
+      "grad_norm": 0.40655484795570374,
+      "learning_rate": 9.584276314284316e-06,
+      "loss": 0.1366,
+      "step": 111
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.574320912361145,
+      "learning_rate": 9.570506887577994e-06,
+      "loss": 0.1338,
+      "step": 112
+    },
+    {
+      "epoch": 0.6611409068746953,
+      "grad_norm": 0.4128205478191376,
+      "learning_rate": 9.556523350824759e-06,
+      "loss": 0.1236,
+      "step": 113
+    },
+    {
+      "epoch": 0.666991711360312,
+      "grad_norm": 0.44907814264297485,
+      "learning_rate": 9.542326359097619e-06,
+      "loss": 0.1377,
+      "step": 114
+    },
+    {
+      "epoch": 0.6728425158459288,
+      "grad_norm": 0.40679454803466797,
+      "learning_rate": 9.527916577469104e-06,
+      "loss": 0.1425,
+      "step": 115
+    },
+    {
+      "epoch": 0.6786933203315456,
+      "grad_norm": 0.42478692531585693,
+      "learning_rate": 9.5132946809801e-06,
+      "loss": 0.1424,
+      "step": 116
+    },
+    {
+      "epoch": 0.6845441248171623,
+      "grad_norm": 0.40595975518226624,
+      "learning_rate": 9.498461354608228e-06,
+      "loss": 0.1268,
+      "step": 117
+    },
+    {
+      "epoch": 0.6903949293027791,
+      "grad_norm": 0.42049211263656616,
+      "learning_rate": 9.483417293235759e-06,
+      "loss": 0.148,
+      "step": 118
+    },
+    {
+      "epoch": 0.6962457337883959,
+      "grad_norm": 0.4690849483013153,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.1323,
+      "step": 119
+    },
+    {
+      "epoch": 0.7020965382740126,
+      "grad_norm": 0.4121830463409424,
+      "learning_rate": 9.452699794345583e-06,
+      "loss": 0.1316,
+      "step": 120
+    },
+    {
+      "epoch": 0.7079473427596294,
+      "grad_norm": 0.4223732352256775,
+      "learning_rate": 9.437027795820373e-06,
+      "loss": 0.1423,
+      "step": 121
+    },
+    {
+      "epoch": 0.7137981472452463,
+      "grad_norm": 0.43553781509399414,
+      "learning_rate": 9.421147940212152e-06,
+      "loss": 0.1451,
+      "step": 122
+    },
+    {
+      "epoch": 0.719648951730863,
+      "grad_norm": 0.3980019688606262,
+      "learning_rate": 9.405060971428924e-06,
+      "loss": 0.1289,
+      "step": 123
+    },
+    {
+      "epoch": 0.7254997562164798,
+      "grad_norm": 0.4621797204017639,
+      "learning_rate": 9.388767643081109e-06,
+      "loss": 0.1376,
+      "step": 124
+    },
+    {
+      "epoch": 0.7313505607020966,
+      "grad_norm": 0.4204331338405609,
+      "learning_rate": 9.372268718446259e-06,
+      "loss": 0.1504,
+      "step": 125
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.4406717121601105,
+      "learning_rate": 9.355564970433288e-06,
+      "loss": 0.1395,
+      "step": 126
+    },
+    {
+      "epoch": 0.7430521696733301,
+      "grad_norm": 0.42246147990226746,
+      "learning_rate": 9.338657181546277e-06,
+      "loss": 0.1403,
+      "step": 127
+    },
+    {
+      "epoch": 0.7489029741589469,
+      "grad_norm": 0.4052499234676361,
+      "learning_rate": 9.321546143847802e-06,
+      "loss": 0.1297,
+      "step": 128
+    },
+    {
+      "epoch": 0.7547537786445636,
+      "grad_norm": 0.44214069843292236,
+      "learning_rate": 9.30423265892184e-06,
+      "loss": 0.1427,
+      "step": 129
+    },
+    {
+      "epoch": 0.7606045831301804,
+      "grad_norm": 0.4202938973903656,
+      "learning_rate": 9.286717537836211e-06,
+      "loss": 0.1426,
+      "step": 130
+    },
+    {
+      "epoch": 0.7664553876157971,
+      "grad_norm": 0.40408894419670105,
+      "learning_rate": 9.269001601104593e-06,
+      "loss": 0.1482,
+      "step": 131
+    },
+    {
+      "epoch": 0.7723061921014139,
+      "grad_norm": 0.43469467759132385,
+      "learning_rate": 9.251085678648072e-06,
+      "loss": 0.1434,
+      "step": 132
+    },
+    {
+      "epoch": 0.7781569965870307,
+      "grad_norm": 0.4173245131969452,
+      "learning_rate": 9.232970609756267e-06,
+      "loss": 0.1304,
+      "step": 133
+    },
+    {
+      "epoch": 0.7840078010726474,
+      "grad_norm": 0.3956865072250366,
+      "learning_rate": 9.214657243048021e-06,
+      "loss": 0.1334,
+      "step": 134
+    },
+    {
+      "epoch": 0.7898586055582643,
+      "grad_norm": 0.43496742844581604,
+      "learning_rate": 9.196146436431635e-06,
+      "loss": 0.1435,
+      "step": 135
+    },
+    {
+      "epoch": 0.7957094100438811,
+      "grad_norm": 0.40430235862731934,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.1406,
+      "step": 136
+    },
+    {
+      "epoch": 0.8015602145294978,
+      "grad_norm": 0.4011284410953522,
+      "learning_rate": 9.158535981313395e-06,
+      "loss": 0.1279,
+      "step": 137
+    },
+    {
+      "epoch": 0.8074110190151146,
+      "grad_norm": 0.4090335965156555,
+      "learning_rate": 9.13943809471159e-06,
+      "loss": 0.141,
+      "step": 138
+    },
+    {
+      "epoch": 0.8132618235007314,
+      "grad_norm": 0.41207408905029297,
+      "learning_rate": 9.120146291919206e-06,
+      "loss": 0.1324,
+      "step": 139
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.400602787733078,
+      "learning_rate": 9.100661476680379e-06,
+      "loss": 0.1338,
+      "step": 140
+    },
+    {
+      "epoch": 0.8249634324719649,
+      "grad_norm": 0.4151029884815216,
+      "learning_rate": 9.08098456178111e-06,
+      "loss": 0.1352,
+      "step": 141
+    },
+    {
+      "epoch": 0.8308142369575817,
+      "grad_norm": 0.4229414463043213,
+      "learning_rate": 9.061116469006504e-06,
+      "loss": 0.1402,
+      "step": 142
+    },
+    {
+      "epoch": 0.8366650414431984,
+      "grad_norm": 0.42491304874420166,
+      "learning_rate": 9.041058129097586e-06,
+      "loss": 0.1234,
+      "step": 143
+    },
+    {
+      "epoch": 0.8425158459288152,
+      "grad_norm": 0.4292084872722626,
+      "learning_rate": 9.020810481707709e-06,
+      "loss": 0.1308,
+      "step": 144
+    },
+    {
+      "epoch": 0.8483666504144319,
+      "grad_norm": 0.43276500701904297,
+      "learning_rate": 9.00037447535852e-06,
+      "loss": 0.1492,
+      "step": 145
+    },
+    {
+      "epoch": 0.8542174549000487,
+      "grad_norm": 0.42224961519241333,
+      "learning_rate": 8.979751067395534e-06,
+      "loss": 0.132,
+      "step": 146
+    },
+    {
+      "epoch": 0.8600682593856656,
+      "grad_norm": 0.5183162689208984,
+      "learning_rate": 8.958941223943292e-06,
+      "loss": 0.1517,
+      "step": 147
+    },
+    {
+      "epoch": 0.8659190638712823,
+      "grad_norm": 0.41768166422843933,
+      "learning_rate": 8.937945919860086e-06,
+      "loss": 0.1413,
+      "step": 148
+    },
+    {
+      "epoch": 0.8717698683568991,
+      "grad_norm": 0.48344236612319946,
+      "learning_rate": 8.916766138692303e-06,
+      "loss": 0.1399,
+      "step": 149
+    },
+    {
+      "epoch": 0.8776206728425159,
+      "grad_norm": 0.4375057518482208,
+      "learning_rate": 8.895402872628352e-06,
+      "loss": 0.1326,
+      "step": 150
+    },
+    {
+      "epoch": 0.8834714773281326,
+      "grad_norm": 0.3658796548843384,
+      "learning_rate": 8.873857122452174e-06,
+      "loss": 0.1215,
+      "step": 151
+    },
+    {
+      "epoch": 0.8893222818137494,
+      "grad_norm": 0.4298015236854553,
+      "learning_rate": 8.852129897496367e-06,
+      "loss": 0.1347,
+      "step": 152
+    },
+    {
+      "epoch": 0.8951730862993662,
+      "grad_norm": 0.39684000611305237,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.143,
+      "step": 153
+    },
+    {
+      "epoch": 0.9010238907849829,
+      "grad_norm": 0.4388231933116913,
+      "learning_rate": 8.808135103035407e-06,
+      "loss": 0.13,
+      "step": 154
+    },
+    {
+      "epoch": 0.9068746952705997,
+      "grad_norm": 0.47847867012023926,
+      "learning_rate": 8.785869594511182e-06,
+      "loss": 0.1443,
+      "step": 155
+    },
+    {
+      "epoch": 0.9127254997562165,
+      "grad_norm": 0.4175593852996826,
+      "learning_rate": 8.763426733072624e-06,
+      "loss": 0.1375,
+      "step": 156
+    },
+    {
+      "epoch": 0.9185763042418332,
+      "grad_norm": 0.4408848285675049,
+      "learning_rate": 8.740807570078419e-06,
+      "loss": 0.149,
+      "step": 157
+    },
+    {
+      "epoch": 0.92442710872745,
+      "grad_norm": 0.41366511583328247,
+      "learning_rate": 8.718013165146275e-06,
+      "loss": 0.1282,
+      "step": 158
+    },
+    {
+      "epoch": 0.9302779132130667,
+      "grad_norm": 0.40209296345710754,
+      "learning_rate": 8.695044586103297e-06,
+      "loss": 0.1328,
+      "step": 159
+    },
+    {
+      "epoch": 0.9361287176986836,
+      "grad_norm": 0.39008352160453796,
+      "learning_rate": 8.671902908935942e-06,
+      "loss": 0.1263,
+      "step": 160
+    },
+    {
+      "epoch": 0.9419795221843004,
+      "grad_norm": 0.741543173789978,
+      "learning_rate": 8.648589217739635e-06,
+      "loss": 0.1348,
+      "step": 161
+    },
+    {
+      "epoch": 0.9478303266699171,
+      "grad_norm": 0.3927006125450134,
+      "learning_rate": 8.625104604667965e-06,
+      "loss": 0.1448,
+      "step": 162
+    },
+    {
+      "epoch": 0.9536811311555339,
+      "grad_norm": 0.3813360035419464,
+      "learning_rate": 8.601450169881533e-06,
+      "loss": 0.1367,
+      "step": 163
+    },
+    {
+      "epoch": 0.9595319356411507,
+      "grad_norm": 0.41232413053512573,
+      "learning_rate": 8.577627021496413e-06,
+      "loss": 0.1333,
+      "step": 164
+    },
+    {
+      "epoch": 0.9653827401267674,
+      "grad_norm": 0.4455775320529938,
+      "learning_rate": 8.553636275532236e-06,
+      "loss": 0.1431,
+      "step": 165
+    },
+    {
+      "epoch": 0.9712335446123842,
+      "grad_norm": 0.4114275574684143,
+      "learning_rate": 8.529479055859918e-06,
+      "loss": 0.1262,
+      "step": 166
+    },
+    {
+      "epoch": 0.977084349098001,
+      "grad_norm": 0.4263303279876709,
+      "learning_rate": 8.505156494148997e-06,
+      "loss": 0.1416,
+      "step": 167
+    },
+    {
+      "epoch": 0.9829351535836177,
+      "grad_norm": 0.38404276967048645,
+      "learning_rate": 8.480669729814635e-06,
+      "loss": 0.1404,
+      "step": 168
+    },
+    {
+      "epoch": 0.9887859580692345,
+      "grad_norm": 0.3970484733581543,
+      "learning_rate": 8.456019909964224e-06,
+      "loss": 0.1311,
+      "step": 169
+    },
+    {
+      "epoch": 0.9946367625548513,
+      "grad_norm": 0.41995933651924133,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.1358,
+      "step": 170
+    },
+    {
+      "epoch": 1.0014627011214041,
+      "grad_norm": 0.47906413674354553,
+      "learning_rate": 8.40623573028327e-06,
+      "loss": 0.1602,
+      "step": 171
+    },
+    {
+      "epoch": 1.007313505607021,
+      "grad_norm": 0.3676239550113678,
+      "learning_rate": 8.381103702643295e-06,
+      "loss": 0.09,
+      "step": 172
+    },
+    {
+      "epoch": 1.0131643100926377,
+      "grad_norm": 0.3158869445323944,
+      "learning_rate": 8.35581328375915e-06,
+      "loss": 0.0749,
+      "step": 173
+    },
+    {
+      "epoch": 1.0190151145782544,
+      "grad_norm": 0.3189470171928406,
+      "learning_rate": 8.330365658386252e-06,
+      "loss": 0.085,
+      "step": 174
+    },
+    {
+      "epoch": 1.0248659190638714,
+      "grad_norm": 0.2992206811904907,
+      "learning_rate": 8.30476201864451e-06,
+      "loss": 0.0758,
+      "step": 175
+    },
+    {
+      "epoch": 1.030716723549488,
+      "grad_norm": 0.36117929220199585,
+      "learning_rate": 8.27900356396249e-06,
+      "loss": 0.0737,
+      "step": 176
+    },
+    {
+      "epoch": 1.0365675280351048,
+      "grad_norm": 0.4092389643192291,
+      "learning_rate": 8.25309150102121e-06,
+      "loss": 0.0874,
+      "step": 177
+    },
+    {
+      "epoch": 1.0424183325207217,
+      "grad_norm": 0.42305558919906616,
+      "learning_rate": 8.227027043697642e-06,
+      "loss": 0.0988,
+      "step": 178
+    },
+    {
+      "epoch": 1.0482691370063384,
+      "grad_norm": 0.34523454308509827,
+      "learning_rate": 8.200811413007808e-06,
+      "loss": 0.0851,
+      "step": 179
+    },
+    {
+      "epoch": 1.054119941491955,
+      "grad_norm": 0.389148086309433,
+      "learning_rate": 8.174445837049614e-06,
+      "loss": 0.0823,
+      "step": 180
+    },
+    {
+      "epoch": 1.059970745977572,
+      "grad_norm": 0.33525988459587097,
+      "learning_rate": 8.147931550945301e-06,
+      "loss": 0.0775,
+      "step": 181
+    },
+    {
+      "epoch": 1.0658215504631887,
+      "grad_norm": 0.3539344370365143,
+      "learning_rate": 8.121269796783585e-06,
+      "loss": 0.0869,
+      "step": 182
+    },
+    {
+      "epoch": 1.0716723549488054,
+      "grad_norm": 0.32239681482315063,
+      "learning_rate": 8.094461823561473e-06,
+      "loss": 0.0769,
+      "step": 183
+    },
+    {
+      "epoch": 1.0775231594344223,
+      "grad_norm": 0.3420362174510956,
+      "learning_rate": 8.06750888712576e-06,
+      "loss": 0.091,
+      "step": 184
+    },
+    {
+      "epoch": 1.083373963920039,
+      "grad_norm": 0.34657928347587585,
+      "learning_rate": 8.040412250114184e-06,
+      "loss": 0.0752,
+      "step": 185
+    },
+    {
+      "epoch": 1.0892247684056557,
+      "grad_norm": 0.3150254786014557,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.0684,
+      "step": 186
+    },
+    {
+      "epoch": 1.0950755728912727,
+      "grad_norm": 0.33900588750839233,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.0846,
+      "step": 187
+    },
+    {
+      "epoch": 1.1009263773768894,
+      "grad_norm": 0.35361960530281067,
+      "learning_rate": 7.958272862621562e-06,
+      "loss": 0.0879,
+      "step": 188
+    },
+    {
+      "epoch": 1.106777181862506,
+      "grad_norm": 0.3507941663265228,
+      "learning_rate": 7.930614183426074e-06,
+      "loss": 0.0773,
+      "step": 189
+    },
+    {
+      "epoch": 1.1126279863481228,
+      "grad_norm": 0.36692172288894653,
+      "learning_rate": 7.902818216626446e-06,
+      "loss": 0.0954,
+      "step": 190
+    },
+    {
+      "epoch": 1.1184787908337397,
+      "grad_norm": 0.33450374007225037,
+      "learning_rate": 7.874886264353035e-06,
+      "loss": 0.0745,
+      "step": 191
+    },
+    {
+      "epoch": 1.1243295953193564,
+      "grad_norm": 0.3424067795276642,
+      "learning_rate": 7.846819635106569e-06,
+      "loss": 0.0838,
+      "step": 192
+    },
+    {
+      "epoch": 1.130180399804973,
+      "grad_norm": 0.33934175968170166,
+      "learning_rate": 7.818619643696863e-06,
+      "loss": 0.0769,
+      "step": 193
+    },
+    {
+      "epoch": 1.13603120429059,
+      "grad_norm": 0.3160100281238556,
+      "learning_rate": 7.790287611181217e-06,
+      "loss": 0.0811,
+      "step": 194
+    },
+    {
+      "epoch": 1.1418820087762067,
+      "grad_norm": 0.2945168912410736,
+      "learning_rate": 7.76182486480253e-06,
+      "loss": 0.0794,
+      "step": 195
+    },
+    {
+      "epoch": 1.1477328132618234,
+      "grad_norm": 0.34128355979919434,
+      "learning_rate": 7.733232737927123e-06,
+      "loss": 0.0753,
+      "step": 196
+    },
+    {
+      "epoch": 1.1535836177474403,
+      "grad_norm": 0.3292410671710968,
+      "learning_rate": 7.70451256998228e-06,
+      "loss": 0.0807,
+      "step": 197
+    },
+    {
+      "epoch": 1.159434422233057,
+      "grad_norm": 0.30368009209632874,
+      "learning_rate": 7.675665706393502e-06,
+      "loss": 0.0774,
+      "step": 198
+    },
+    {
+      "epoch": 1.1652852267186737,
+      "grad_norm": 0.3382299542427063,
+      "learning_rate": 7.646693498521472e-06,
+      "loss": 0.0801,
+      "step": 199
+    },
+    {
+      "epoch": 1.1711360312042907,
+      "grad_norm": 0.34679096937179565,
+      "learning_rate": 7.617597303598754e-06,
+      "loss": 0.0828,
+      "step": 200
+    },
+    {
+      "epoch": 1.1769868356899074,
+      "grad_norm": 0.3604985773563385,
+      "learning_rate": 7.588378484666214e-06,
+      "loss": 0.0857,
+      "step": 201
+    },
+    {
+      "epoch": 1.182837640175524,
+      "grad_norm": 0.3484993278980255,
+      "learning_rate": 7.559038410509161e-06,
+      "loss": 0.0853,
+      "step": 202
+    },
+    {
+      "epoch": 1.188688444661141,
+      "grad_norm": 0.3147986829280853,
+      "learning_rate": 7.529578455593232e-06,
+      "loss": 0.0833,
+      "step": 203
+    },
+    {
+      "epoch": 1.1945392491467577,
+      "grad_norm": 0.3428245782852173,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0829,
+      "step": 204
+    },
+    {
+      "epoch": 1.2003900536323744,
+      "grad_norm": 0.31704169511795044,
+      "learning_rate": 7.47030442936232e-06,
+      "loss": 0.0826,
+      "step": 205
+    },
+    {
+      "epoch": 1.2062408581179913,
+      "grad_norm": 0.3161751329898834,
+      "learning_rate": 7.440493134799425e-06,
+      "loss": 0.0774,
+      "step": 206
+    },
+    {
+      "epoch": 1.212091662603608,
+      "grad_norm": 0.3535175919532776,
+      "learning_rate": 7.4105675128517456e-06,
+      "loss": 0.0728,
+      "step": 207
+    },
+    {
+      "epoch": 1.2179424670892247,
+      "grad_norm": 0.37694627046585083,
+      "learning_rate": 7.380528965415501e-06,
+      "loss": 0.1014,
+      "step": 208
+    },
+    {
+      "epoch": 1.2237932715748416,
+      "grad_norm": 0.36685872077941895,
+      "learning_rate": 7.35037889967702e-06,
+      "loss": 0.0885,
+      "step": 209
+    },
+    {
+      "epoch": 1.2296440760604583,
+      "grad_norm": 0.3464377522468567,
+      "learning_rate": 7.320118728046818e-06,
+      "loss": 0.0875,
+      "step": 210
+    },
+    {
+      "epoch": 1.235494880546075,
+      "grad_norm": 0.30345961451530457,
+      "learning_rate": 7.289749868093432e-06,
+      "loss": 0.0784,
+      "step": 211
+    },
+    {
+      "epoch": 1.2413456850316917,
+      "grad_norm": 0.34137392044067383,
+      "learning_rate": 7.259273742477017e-06,
+      "loss": 0.0741,
+      "step": 212
+    },
+    {
+      "epoch": 1.2471964895173087,
+      "grad_norm": 0.3188891112804413,
+      "learning_rate": 7.2286917788826926e-06,
+      "loss": 0.0782,
+      "step": 213
+    },
+    {
+      "epoch": 1.2530472940029254,
+      "grad_norm": 0.30841705203056335,
+      "learning_rate": 7.19800540995367e-06,
+      "loss": 0.0768,
+      "step": 214
+    },
+    {
+      "epoch": 1.258898098488542,
+      "grad_norm": 0.3702380657196045,
+      "learning_rate": 7.167216073224136e-06,
+      "loss": 0.0851,
+      "step": 215
+    },
+    {
+      "epoch": 1.264748902974159,
+      "grad_norm": 0.3240349590778351,
+      "learning_rate": 7.136325211051905e-06,
+      "loss": 0.0756,
+      "step": 216
+    },
+    {
+      "epoch": 1.2705997074597757,
+      "grad_norm": 0.3365533649921417,
+      "learning_rate": 7.1053342705508564e-06,
+      "loss": 0.0835,
+      "step": 217
+    },
+    {
+      "epoch": 1.2764505119453924,
+      "grad_norm": 0.2976110577583313,
+      "learning_rate": 7.074244703523137e-06,
+      "loss": 0.0667,
+      "step": 218
+    },
+    {
+      "epoch": 1.2823013164310093,
+      "grad_norm": 0.3380391597747803,
+      "learning_rate": 7.043057966391158e-06,
+      "loss": 0.0822,
+      "step": 219
+    },
+    {
+      "epoch": 1.288152120916626,
+      "grad_norm": 0.3523262143135071,
+      "learning_rate": 7.011775520129363e-06,
+      "loss": 0.0776,
+      "step": 220
+    },
+    {
+      "epoch": 1.2940029254022427,
+      "grad_norm": 0.29708200693130493,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.0809,
+      "step": 221
+    },
+    {
+      "epoch": 1.2998537298878596,
+      "grad_norm": 0.3353002369403839,
+      "learning_rate": 6.948929366463397e-06,
+      "loss": 0.0698,
+      "step": 222
+    },
+    {
+      "epoch": 1.3057045343734763,
+      "grad_norm": 0.34924203157424927,
+      "learning_rate": 6.9173686031512595e-06,
+      "loss": 0.0923,
+      "step": 223
+    },
+    {
+      "epoch": 1.311555338859093,
+      "grad_norm": 0.31901872158050537,
+      "learning_rate": 6.885718018755448e-06,
+      "loss": 0.0806,
+      "step": 224
+    },
+    {
+      "epoch": 1.31740614334471,
+      "grad_norm": 0.33020636439323425,
+      "learning_rate": 6.8539790959798045e-06,
+      "loss": 0.0778,
+      "step": 225
+    },
+    {
+      "epoch": 1.3232569478303267,
+      "grad_norm": 0.35056766867637634,
+      "learning_rate": 6.822153321666469e-06,
+      "loss": 0.0827,
+      "step": 226
+    },
+    {
+      "epoch": 1.3291077523159434,
+      "grad_norm": 0.34175387024879456,
+      "learning_rate": 6.790242186726231e-06,
+      "loss": 0.082,
+      "step": 227
+    },
+    {
+      "epoch": 1.3349585568015603,
+      "grad_norm": 0.34124261140823364,
+      "learning_rate": 6.758247186068684e-06,
+      "loss": 0.084,
+      "step": 228
+    },
+    {
+      "epoch": 1.340809361287177,
+      "grad_norm": 0.3028365969657898,
+      "learning_rate": 6.7261698185322e-06,
+      "loss": 0.0768,
+      "step": 229
+    },
+    {
+      "epoch": 1.3466601657727937,
+      "grad_norm": 0.3365366756916046,
+      "learning_rate": 6.6940115868137065e-06,
+      "loss": 0.076,
+      "step": 230
+    },
+    {
+      "epoch": 1.3525109702584106,
+      "grad_norm": 0.30919474363327026,
+      "learning_rate": 6.6617739973982985e-06,
+      "loss": 0.0789,
+      "step": 231
+    },
+    {
+      "epoch": 1.3583617747440273,
+      "grad_norm": 0.3369212746620178,
+      "learning_rate": 6.629458560488664e-06,
+      "loss": 0.0945,
+      "step": 232
+    },
+    {
+      "epoch": 1.364212579229644,
+      "grad_norm": 0.3106522560119629,
+      "learning_rate": 6.597066789934336e-06,
+      "loss": 0.081,
+      "step": 233
+    },
+    {
+      "epoch": 1.370063383715261,
+      "grad_norm": 0.36917534470558167,
+      "learning_rate": 6.5646002031607726e-06,
+      "loss": 0.0842,
+      "step": 234
+    },
+    {
+      "epoch": 1.3759141882008776,
+      "grad_norm": 0.33988648653030396,
+      "learning_rate": 6.5320603210982745e-06,
+      "loss": 0.0859,
+      "step": 235
+    },
+    {
+      "epoch": 1.3817649926864943,
+      "grad_norm": 0.34712544083595276,
+      "learning_rate": 6.499448668110735e-06,
+      "loss": 0.0884,
+      "step": 236
+    },
+    {
+      "epoch": 1.3876157971721113,
+      "grad_norm": 0.3763306140899658,
+      "learning_rate": 6.466766771924231e-06,
+      "loss": 0.0861,
+      "step": 237
+    },
+    {
+      "epoch": 1.393466601657728,
+      "grad_norm": 0.33518311381340027,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.0798,
+      "step": 238
+    },
+    {
+      "epoch": 1.3993174061433447,
+      "grad_norm": 0.31457552313804626,
+      "learning_rate": 6.401198377239979e-06,
+      "loss": 0.0788,
+      "step": 239
+    },
+    {
+      "epoch": 1.4051682106289616,
+      "grad_norm": 0.3552372455596924,
+      "learning_rate": 6.368314950360416e-06,
+      "loss": 0.0806,
+      "step": 240
+    },
+    {
+      "epoch": 1.4110190151145783,
+      "grad_norm": 0.32624173164367676,
+      "learning_rate": 6.3353674233743585e-06,
+      "loss": 0.0852,
+      "step": 241
+    },
+    {
+      "epoch": 1.416869819600195,
+      "grad_norm": 0.36660850048065186,
+      "learning_rate": 6.302357339742245e-06,
+      "loss": 0.0887,
+      "step": 242
+    },
+    {
+      "epoch": 1.422720624085812,
+      "grad_norm": 0.30113551020622253,
+      "learning_rate": 6.269286245855039e-06,
+      "loss": 0.0733,
+      "step": 243
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.3478698134422302,
+      "learning_rate": 6.236155690961795e-06,
+      "loss": 0.0733,
+      "step": 244
+    },
+    {
+      "epoch": 1.4344222330570453,
+      "grad_norm": 0.346223384141922,
+      "learning_rate": 6.202967227097073e-06,
+      "loss": 0.0892,
+      "step": 245
+    },
+    {
+      "epoch": 1.4402730375426622,
+      "grad_norm": 0.3341302275657654,
+      "learning_rate": 6.169722409008244e-06,
+      "loss": 0.0797,
+      "step": 246
+    },
+    {
+      "epoch": 1.446123842028279,
+      "grad_norm": 0.3604235351085663,
+      "learning_rate": 6.136422794082645e-06,
+      "loss": 0.0697,
+      "step": 247
+    },
+    {
+      "epoch": 1.4519746465138956,
+      "grad_norm": 0.3553491234779358,
+      "learning_rate": 6.10306994227463e-06,
+      "loss": 0.0789,
+      "step": 248
+    },
+    {
+      "epoch": 1.4578254509995126,
+      "grad_norm": 0.358963280916214,
+      "learning_rate": 6.0696654160324875e-06,
+      "loss": 0.0809,
+      "step": 249
+    },
+    {
+      "epoch": 1.4636762554851293,
+      "grad_norm": 0.3794144093990326,
+      "learning_rate": 6.0362107802252486e-06,
+      "loss": 0.0817,
+      "step": 250
+    },
+    {
+      "epoch": 1.469527059970746,
+      "grad_norm": 0.3239617943763733,
+      "learning_rate": 6.002707602069377e-06,
+      "loss": 0.0837,
+      "step": 251
+    },
+    {
+      "epoch": 1.4753778644563629,
+      "grad_norm": 0.3182874321937561,
+      "learning_rate": 5.9691574510553505e-06,
+      "loss": 0.0877,
+      "step": 252
+    },
+    {
+      "epoch": 1.4812286689419796,
+      "grad_norm": 0.3259419798851013,
+      "learning_rate": 5.935561898874142e-06,
+      "loss": 0.0846,
+      "step": 253
+    },
+    {
+      "epoch": 1.4870794734275963,
+      "grad_norm": 0.3229186236858368,
+      "learning_rate": 5.901922519343586e-06,
+      "loss": 0.0785,
+      "step": 254
+    },
+    {
+      "epoch": 1.4929302779132132,
+      "grad_norm": 0.3261856734752655,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.0893,
+      "step": 255
+    },
+    {
+      "epoch": 1.49878108239883,
+      "grad_norm": 0.3506629168987274,
+      "learning_rate": 5.834518583697628e-06,
+      "loss": 0.0953,
+      "step": 256
+    },
+    {
+      "epoch": 1.5046318868844466,
+      "grad_norm": 0.3554547131061554,
+      "learning_rate": 5.800757185188195e-06,
+      "loss": 0.0806,
+      "step": 257
+    },
+    {
+      "epoch": 1.5104826913700635,
+      "grad_norm": 0.3573915958404541,
+      "learning_rate": 5.766958274393428e-06,
+      "loss": 0.0875,
+      "step": 258
+    },
+    {
+      "epoch": 1.51633349585568,
+      "grad_norm": 0.34284883737564087,
+      "learning_rate": 5.733123434657704e-06,
+      "loss": 0.0906,
+      "step": 259
+    },
+    {
+      "epoch": 1.522184300341297,
+      "grad_norm": 0.3178277015686035,
+      "learning_rate": 5.699254251008524e-06,
+      "loss": 0.0731,
+      "step": 260
+    },
+    {
+      "epoch": 1.5280351048269138,
+      "grad_norm": 0.40219858288764954,
+      "learning_rate": 5.66535231008227e-06,
+      "loss": 0.0817,
+      "step": 261
+    },
+    {
+      "epoch": 1.5338859093125303,
+      "grad_norm": 0.35268712043762207,
+      "learning_rate": 5.631419200049867e-06,
+      "loss": 0.0795,
+      "step": 262
+    },
+    {
+      "epoch": 1.5397367137981472,
+      "grad_norm": 0.3267902433872223,
+      "learning_rate": 5.597456510542395e-06,
+      "loss": 0.0688,
+      "step": 263
+    },
+    {
+      "epoch": 1.5455875182837642,
+      "grad_norm": 0.3811274766921997,
+      "learning_rate": 5.5634658325766066e-06,
+      "loss": 0.0812,
+      "step": 264
+    },
+    {
+      "epoch": 1.5514383227693807,
+      "grad_norm": 0.3165196180343628,
+      "learning_rate": 5.529448758480408e-06,
+      "loss": 0.0693,
+      "step": 265
+    },
+    {
+      "epoch": 1.5572891272549976,
+      "grad_norm": 0.3585417866706848,
+      "learning_rate": 5.495406881818256e-06,
+      "loss": 0.0853,
+      "step": 266
+    },
+    {
+      "epoch": 1.5631399317406145,
+      "grad_norm": 0.30655720829963684,
+      "learning_rate": 5.46134179731651e-06,
+      "loss": 0.0847,
+      "step": 267
+    },
+    {
+      "epoch": 1.568990736226231,
+      "grad_norm": 0.2977589964866638,
+      "learning_rate": 5.427255100788726e-06,
+      "loss": 0.0801,
+      "step": 268
+    },
+    {
+      "epoch": 1.574841540711848,
+      "grad_norm": 0.3374764323234558,
+      "learning_rate": 5.393148389060893e-06,
+      "loss": 0.0761,
+      "step": 269
+    },
+    {
+      "epoch": 1.5806923451974646,
+      "grad_norm": 0.33393600583076477,
+      "learning_rate": 5.359023259896638e-06,
+      "loss": 0.0827,
+      "step": 270
+    },
+    {
+      "epoch": 1.5865431496830813,
+      "grad_norm": 0.35629692673683167,
+      "learning_rate": 5.3248813119223665e-06,
+      "loss": 0.0833,
+      "step": 271
+    },
+    {
+      "epoch": 1.5923939541686982,
+      "grad_norm": 0.3579968810081482,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.0883,
+      "step": 272
+    },
+    {
+      "epoch": 1.598244758654315,
+      "grad_norm": 0.33415958285331726,
+      "learning_rate": 5.2565533579139484e-06,
+      "loss": 0.0811,
+      "step": 273
+    },
+    {
+      "epoch": 1.6040955631399316,
+      "grad_norm": 0.31935596466064453,
+      "learning_rate": 5.222370552772353e-06,
+      "loss": 0.0852,
+      "step": 274
+    },
+    {
+      "epoch": 1.6099463676255485,
+      "grad_norm": 0.35256752371788025,
+      "learning_rate": 5.188177330455886e-06,
+      "loss": 0.0913,
+      "step": 275
+    },
+    {
+      "epoch": 1.6157971721111652,
+      "grad_norm": 0.31540942192077637,
+      "learning_rate": 5.153975292780852e-06,
+      "loss": 0.0789,
+      "step": 276
+    },
+    {
+      "epoch": 1.621647976596782,
+      "grad_norm": 0.3884231448173523,
+      "learning_rate": 5.119766041976516e-06,
+      "loss": 0.0784,
+      "step": 277
+    },
+    {
+      "epoch": 1.6274987810823989,
+      "grad_norm": 0.30289870500564575,
+      "learning_rate": 5.085551180610046e-06,
+      "loss": 0.073,
+      "step": 278
+    },
+    {
+      "epoch": 1.6333495855680156,
+      "grad_norm": 0.3469166159629822,
+      "learning_rate": 5.05133231151145e-06,
+      "loss": 0.0781,
+      "step": 279
+    },
+    {
+      "epoch": 1.6392003900536323,
+      "grad_norm": 0.3332676887512207,
+      "learning_rate": 5.017111037698477e-06,
+      "loss": 0.0837,
+      "step": 280
+    },
+    {
+      "epoch": 1.6450511945392492,
+      "grad_norm": 0.3515254557132721,
+      "learning_rate": 4.9828889623015265e-06,
+      "loss": 0.0945,
+      "step": 281
+    },
+    {
+      "epoch": 1.650901999024866,
+      "grad_norm": 0.3309212923049927,
+      "learning_rate": 4.948667688488552e-06,
+      "loss": 0.0773,
+      "step": 282
+    },
+    {
+      "epoch": 1.6567528035104826,
+      "grad_norm": 0.3406410217285156,
+      "learning_rate": 4.9144488193899546e-06,
+      "loss": 0.0742,
+      "step": 283
+    },
+    {
+      "epoch": 1.6626036079960995,
+      "grad_norm": 0.3194100260734558,
+      "learning_rate": 4.880233958023486e-06,
+      "loss": 0.0768,
+      "step": 284
+    },
+    {
+      "epoch": 1.6684544124817162,
+      "grad_norm": 0.34699711203575134,
+      "learning_rate": 4.846024707219149e-06,
+      "loss": 0.0853,
+      "step": 285
+    },
+    {
+      "epoch": 1.674305216967333,
+      "grad_norm": 0.3401515781879425,
+      "learning_rate": 4.811822669544115e-06,
+      "loss": 0.0755,
+      "step": 286
+    },
+    {
+      "epoch": 1.6801560214529498,
+      "grad_norm": 0.3512323498725891,
+      "learning_rate": 4.777629447227649e-06,
+      "loss": 0.0928,
+      "step": 287
+    },
+    {
+      "epoch": 1.6860068259385665,
+      "grad_norm": 0.3097745478153229,
+      "learning_rate": 4.7434466420860515e-06,
+      "loss": 0.0727,
+      "step": 288
+    },
+    {
+      "epoch": 1.6918576304241832,
+      "grad_norm": 0.2933128774166107,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.0729,
+      "step": 289
+    },
+    {
+      "epoch": 1.6977084349098002,
+      "grad_norm": 0.35171079635620117,
+      "learning_rate": 4.675118688077634e-06,
+      "loss": 0.081,
+      "step": 290
+    },
+    {
+      "epoch": 1.7035592393954169,
+      "grad_norm": 0.3128647804260254,
+      "learning_rate": 4.640976740103363e-06,
+      "loss": 0.0783,
+      "step": 291
+    },
+    {
+      "epoch": 1.7094100438810336,
+      "grad_norm": 0.35127922892570496,
+      "learning_rate": 4.606851610939108e-06,
+      "loss": 0.0812,
+      "step": 292
+    },
+    {
+      "epoch": 1.7152608483666505,
+      "grad_norm": 0.30880433320999146,
+      "learning_rate": 4.572744899211275e-06,
+      "loss": 0.0819,
+      "step": 293
+    },
+    {
+      "epoch": 1.7211116528522672,
+      "grad_norm": 0.32968375086784363,
+      "learning_rate": 4.53865820268349e-06,
+      "loss": 0.0816,
+      "step": 294
+    },
+    {
+      "epoch": 1.726962457337884,
+      "grad_norm": 0.3447258174419403,
+      "learning_rate": 4.504593118181745e-06,
+      "loss": 0.0712,
+      "step": 295
+    },
+    {
+      "epoch": 1.7328132618235008,
+      "grad_norm": 0.31902605295181274,
+      "learning_rate": 4.470551241519594e-06,
+      "loss": 0.0861,
+      "step": 296
+    },
+    {
+      "epoch": 1.7386640663091175,
+      "grad_norm": 0.34594473242759705,
+      "learning_rate": 4.436534167423395e-06,
+      "loss": 0.0767,
+      "step": 297
+    },
+    {
+      "epoch": 1.7445148707947342,
+      "grad_norm": 0.341180682182312,
+      "learning_rate": 4.402543489457607e-06,
+      "loss": 0.0841,
+      "step": 298
+    },
+    {
+      "epoch": 1.7503656752803511,
+      "grad_norm": 0.30309170484542847,
+      "learning_rate": 4.368580799950133e-06,
+      "loss": 0.081,
+      "step": 299
+    },
+    {
+      "epoch": 1.7562164797659678,
+      "grad_norm": 0.2895878553390503,
+      "learning_rate": 4.334647689917734e-06,
+      "loss": 0.0667,
+      "step": 300
+    },
+    {
+      "epoch": 1.7620672842515845,
+      "grad_norm": 0.33328762650489807,
+      "learning_rate": 4.300745748991478e-06,
+      "loss": 0.0841,
+      "step": 301
+    },
+    {
+      "epoch": 1.7679180887372015,
+      "grad_norm": 0.34671878814697266,
+      "learning_rate": 4.266876565342298e-06,
+      "loss": 0.0768,
+      "step": 302
+    },
+    {
+      "epoch": 1.7737688932228182,
+      "grad_norm": 0.3152706027030945,
+      "learning_rate": 4.233041725606573e-06,
+      "loss": 0.0816,
+      "step": 303
+    },
+    {
+      "epoch": 1.7796196977084349,
+      "grad_norm": 0.32463833689689636,
+      "learning_rate": 4.199242814811807e-06,
+      "loss": 0.0805,
+      "step": 304
+    },
+    {
+      "epoch": 1.7854705021940518,
+      "grad_norm": 0.33821901679039,
+      "learning_rate": 4.1654814163023735e-06,
+      "loss": 0.075,
+      "step": 305
+    },
+    {
+      "epoch": 1.7913213066796685,
+      "grad_norm": 0.31825628876686096,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.0769,
+      "step": 306
+    },
+    {
+      "epoch": 1.7971721111652852,
+      "grad_norm": 0.31411388516426086,
+      "learning_rate": 4.098077480656415e-06,
+      "loss": 0.0788,
+      "step": 307
+    },
+    {
+      "epoch": 1.8030229156509021,
+      "grad_norm": 0.31883758306503296,
+      "learning_rate": 4.064438101125859e-06,
+      "loss": 0.0741,
+      "step": 308
+    },
+    {
+      "epoch": 1.8088737201365188,
+      "grad_norm": 0.383833646774292,
+      "learning_rate": 4.03084254894465e-06,
+      "loss": 0.0888,
+      "step": 309
+    },
+    {
+      "epoch": 1.8147245246221355,
+      "grad_norm": 0.3364141285419464,
+      "learning_rate": 3.997292397930624e-06,
+      "loss": 0.0689,
+      "step": 310
+    },
+    {
+      "epoch": 1.8205753291077524,
+      "grad_norm": 0.31626763939857483,
+      "learning_rate": 3.963789219774753e-06,
+      "loss": 0.0741,
+      "step": 311
+    },
+    {
+      "epoch": 1.8264261335933691,
+      "grad_norm": 0.31046804785728455,
+      "learning_rate": 3.930334583967514e-06,
+      "loss": 0.0787,
+      "step": 312
+    },
+    {
+      "epoch": 1.8322769380789858,
+      "grad_norm": 0.3264026641845703,
+      "learning_rate": 3.896930057725372e-06,
+      "loss": 0.078,
+      "step": 313
+    },
+    {
+      "epoch": 1.8381277425646028,
+      "grad_norm": 0.32011500000953674,
+      "learning_rate": 3.863577205917356e-06,
+      "loss": 0.0757,
+      "step": 314
+    },
+    {
+      "epoch": 1.8439785470502192,
+      "grad_norm": 0.3323825001716614,
+      "learning_rate": 3.8302775909917585e-06,
+      "loss": 0.0831,
+      "step": 315
+    },
+    {
+      "epoch": 1.8498293515358362,
+      "grad_norm": 0.3106033504009247,
+      "learning_rate": 3.7970327729029288e-06,
+      "loss": 0.0742,
+      "step": 316
+    },
+    {
+      "epoch": 1.855680156021453,
+      "grad_norm": 0.3245903551578522,
+      "learning_rate": 3.7638443090382067e-06,
+      "loss": 0.0786,
+      "step": 317
+    },
+    {
+      "epoch": 1.8615309605070696,
+      "grad_norm": 0.31213557720184326,
+      "learning_rate": 3.730713754144961e-06,
+      "loss": 0.0691,
+      "step": 318
+    },
+    {
+      "epoch": 1.8673817649926865,
+      "grad_norm": 0.33322617411613464,
+      "learning_rate": 3.6976426602577565e-06,
+      "loss": 0.087,
+      "step": 319
+    },
+    {
+      "epoch": 1.8732325694783034,
+      "grad_norm": 0.32928356528282166,
+      "learning_rate": 3.6646325766256423e-06,
+      "loss": 0.0692,
+      "step": 320
+    },
+    {
+      "epoch": 1.87908337396392,
+      "grad_norm": 0.30873045325279236,
+      "learning_rate": 3.6316850496395863e-06,
+      "loss": 0.0729,
+      "step": 321
+    },
+    {
+      "epoch": 1.8849341784495368,
+      "grad_norm": 0.3300439715385437,
+      "learning_rate": 3.598801622760021e-06,
+      "loss": 0.0712,
+      "step": 322
+    },
+    {
+      "epoch": 1.8907849829351537,
+      "grad_norm": 0.3383248746395111,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.0658,
+      "step": 323
+    },
+    {
+      "epoch": 1.8966357874207702,
+      "grad_norm": 0.3341819643974304,
+      "learning_rate": 3.5332332280757706e-06,
+      "loss": 0.081,
+      "step": 324
+    },
+    {
+      "epoch": 1.9024865919063871,
+      "grad_norm": 0.32250940799713135,
+      "learning_rate": 3.5005513318892666e-06,
+      "loss": 0.0796,
+      "step": 325
+    },
+    {
+      "epoch": 1.908337396392004,
+      "grad_norm": 0.4472445547580719,
+      "learning_rate": 3.4679396789017263e-06,
+      "loss": 0.0882,
+      "step": 326
+    },
+    {
+      "epoch": 1.9141882008776205,
+      "grad_norm": 0.31572669744491577,
+      "learning_rate": 3.4353997968392295e-06,
+      "loss": 0.0656,
+      "step": 327
+    },
+    {
+      "epoch": 1.9200390053632375,
+      "grad_norm": 0.3064400255680084,
+      "learning_rate": 3.402933210065665e-06,
+      "loss": 0.0796,
+      "step": 328
+    },
+    {
+      "epoch": 1.9258898098488544,
+      "grad_norm": 0.3014156222343445,
+      "learning_rate": 3.3705414395113354e-06,
+      "loss": 0.0763,
+      "step": 329
+    },
+    {
+      "epoch": 1.9317406143344709,
+      "grad_norm": 0.3247920870780945,
+      "learning_rate": 3.3382260026017027e-06,
+      "loss": 0.0751,
+      "step": 330
+    },
+    {
+      "epoch": 1.9375914188200878,
+      "grad_norm": 0.32763242721557617,
+      "learning_rate": 3.305988413186295e-06,
+      "loss": 0.0684,
+      "step": 331
+    },
+    {
+      "epoch": 1.9434422233057045,
+      "grad_norm": 0.3187495470046997,
+      "learning_rate": 3.2738301814678015e-06,
+      "loss": 0.0643,
+      "step": 332
+    },
+    {
+      "epoch": 1.9492930277913212,
+      "grad_norm": 0.33601319789886475,
+      "learning_rate": 3.241752813931316e-06,
+      "loss": 0.0842,
+      "step": 333
+    },
+    {
+      "epoch": 1.955143832276938,
+      "grad_norm": 0.3197375237941742,
+      "learning_rate": 3.2097578132737716e-06,
+      "loss": 0.0655,
+      "step": 334
+    },
+    {
+      "epoch": 1.9609946367625548,
+      "grad_norm": 0.35822373628616333,
+      "learning_rate": 3.1778466783335328e-06,
+      "loss": 0.0921,
+      "step": 335
+    },
+    {
+      "epoch": 1.9668454412481715,
+      "grad_norm": 0.31587547063827515,
+      "learning_rate": 3.1460209040201967e-06,
+      "loss": 0.0795,
+      "step": 336
+    },
+    {
+      "epoch": 1.9726962457337884,
+      "grad_norm": 0.3147113621234894,
+      "learning_rate": 3.114281981244553e-06,
+      "loss": 0.0729,
+      "step": 337
+    },
+    {
+      "epoch": 1.9785470502194051,
+      "grad_norm": 0.33007726073265076,
+      "learning_rate": 3.082631396848743e-06,
+      "loss": 0.0802,
+      "step": 338
+    },
+    {
+      "epoch": 1.9843978547050218,
+      "grad_norm": 0.3043513894081116,
+      "learning_rate": 3.0510706335366034e-06,
+      "loss": 0.0746,
+      "step": 339
+    },
+    {
+      "epoch": 1.9902486591906388,
+      "grad_norm": 0.3211682438850403,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.078,
+      "step": 340
+    },
+    {
+      "epoch": 1.9960994636762555,
+      "grad_norm": 0.3464657962322235,
+      "learning_rate": 2.9882244798706372e-06,
+      "loss": 0.0711,
+      "step": 341
+    },
+    {
+      "epoch": 2.0029254022428082,
+      "grad_norm": 0.306328684091568,
+      "learning_rate": 2.956942033608843e-06,
+      "loss": 0.0624,
+      "step": 342
+    },
+    {
+      "epoch": 2.008776206728425,
+      "grad_norm": 0.24574756622314453,
+      "learning_rate": 2.9257552964768644e-06,
+      "loss": 0.0475,
+      "step": 343
+    },
+    {
+      "epoch": 2.014627011214042,
+      "grad_norm": 0.2128523290157318,
+      "learning_rate": 2.8946657294491452e-06,
+      "loss": 0.0607,
+      "step": 344
+    },
+    {
+      "epoch": 2.0204778156996586,
+      "grad_norm": 0.19593936204910278,
+      "learning_rate": 2.863674788948097e-06,
+      "loss": 0.0443,
+      "step": 345
+    },
+    {
+      "epoch": 2.0263286201852755,
+      "grad_norm": 0.2186254858970642,
+      "learning_rate": 2.832783926775865e-06,
+      "loss": 0.0546,
+      "step": 346
+    },
+    {
+      "epoch": 2.0321794246708924,
+      "grad_norm": 0.2001432478427887,
+      "learning_rate": 2.8019945900463307e-06,
+      "loss": 0.0463,
+      "step": 347
+    },
+    {
+      "epoch": 2.038030229156509,
+      "grad_norm": 0.2021595686674118,
+      "learning_rate": 2.771308221117309e-06,
+      "loss": 0.0467,
+      "step": 348
+    },
+    {
+      "epoch": 2.043881033642126,
+      "grad_norm": 0.21800445020198822,
+      "learning_rate": 2.740726257522987e-06,
+      "loss": 0.0537,
+      "step": 349
+    },
+    {
+      "epoch": 2.0497318381277427,
+      "grad_norm": 0.24673891067504883,
+      "learning_rate": 2.7102501319065706e-06,
+      "loss": 0.0524,
+      "step": 350
+    },
+    {
+      "epoch": 2.055582642613359,
+      "grad_norm": 0.2493050992488861,
+      "learning_rate": 2.6798812719531843e-06,
+      "loss": 0.0566,
+      "step": 351
+    },
+    {
+      "epoch": 2.061433447098976,
+      "grad_norm": 0.2142155021429062,
+      "learning_rate": 2.6496211003229795e-06,
+      "loss": 0.0464,
+      "step": 352
+    },
+    {
+      "epoch": 2.067284251584593,
+      "grad_norm": 0.22218072414398193,
+      "learning_rate": 2.6194710345845e-06,
+      "loss": 0.0501,
+      "step": 353
+    },
+    {
+      "epoch": 2.0731350560702095,
+      "grad_norm": 0.22646678984165192,
+      "learning_rate": 2.5894324871482557e-06,
+      "loss": 0.0462,
+      "step": 354
+    },
+    {
+      "epoch": 2.0789858605558265,
+      "grad_norm": 0.21073314547538757,
+      "learning_rate": 2.559506865200576e-06,
+      "loss": 0.0439,
+      "step": 355
+    },
+    {
+      "epoch": 2.0848366650414434,
+      "grad_norm": 0.19907771050930023,
+      "learning_rate": 2.529695570637679e-06,
+      "loss": 0.0458,
+      "step": 356
+    },
+    {
+      "epoch": 2.09068746952706,
+      "grad_norm": 0.21957091987133026,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.0552,
+      "step": 357
+    },
+    {
+      "epoch": 2.096538274012677,
+      "grad_norm": 0.19745470583438873,
+      "learning_rate": 2.4704215444067684e-06,
+      "loss": 0.0412,
+      "step": 358
+    },
+    {
+      "epoch": 2.1023890784982937,
+      "grad_norm": 0.23495222628116608,
+      "learning_rate": 2.4409615894908407e-06,
+      "loss": 0.0521,
+      "step": 359
+    },
+    {
+      "epoch": 2.10823988298391,
+      "grad_norm": 0.23315241932868958,
+      "learning_rate": 2.411621515333788e-06,
+      "loss": 0.0519,
+      "step": 360
+    },
+    {
+      "epoch": 2.114090687469527,
+      "grad_norm": 0.23338022828102112,
+      "learning_rate": 2.3824026964012487e-06,
+      "loss": 0.0523,
+      "step": 361
+    },
+    {
+      "epoch": 2.119941491955144,
+      "grad_norm": 0.21098627150058746,
+      "learning_rate": 2.35330650147853e-06,
+      "loss": 0.0552,
+      "step": 362
+    },
+    {
+      "epoch": 2.1257922964407605,
+      "grad_norm": 0.20283359289169312,
+      "learning_rate": 2.324334293606499e-06,
+      "loss": 0.044,
+      "step": 363
+    },
+    {
+      "epoch": 2.1316431009263774,
+      "grad_norm": 0.21483571827411652,
+      "learning_rate": 2.2954874300177197e-06,
+      "loss": 0.0433,
+      "step": 364
+    },
+    {
+      "epoch": 2.1374939054119944,
+      "grad_norm": 0.2035175859928131,
+      "learning_rate": 2.266767262072878e-06,
+      "loss": 0.0472,
+      "step": 365
+    },
+    {
+      "epoch": 2.143344709897611,
+      "grad_norm": 0.21213766932487488,
+      "learning_rate": 2.238175135197471e-06,
+      "loss": 0.053,
+      "step": 366
+    },
+    {
+      "epoch": 2.1491955143832278,
+      "grad_norm": 0.2157718688249588,
+      "learning_rate": 2.2097123888187825e-06,
+      "loss": 0.05,
+      "step": 367
+    },
+    {
+      "epoch": 2.1550463188688447,
+      "grad_norm": 0.19376371800899506,
+      "learning_rate": 2.181380356303139e-06,
+      "loss": 0.0397,
+      "step": 368
+    },
+    {
+      "epoch": 2.160897123354461,
+      "grad_norm": 0.21883581578731537,
+      "learning_rate": 2.1531803648934333e-06,
+      "loss": 0.0446,
+      "step": 369
+    },
+    {
+      "epoch": 2.166747927840078,
+      "grad_norm": 0.21257570385932922,
+      "learning_rate": 2.1251137356469677e-06,
+      "loss": 0.0476,
+      "step": 370
+    },
+    {
+      "epoch": 2.172598732325695,
+      "grad_norm": 0.21544501185417175,
+      "learning_rate": 2.0971817833735548e-06,
+      "loss": 0.0499,
+      "step": 371
+    },
+    {
+      "epoch": 2.1784495368113115,
+      "grad_norm": 0.18301881849765778,
+      "learning_rate": 2.069385816573928e-06,
+      "loss": 0.0392,
+      "step": 372
+    },
+    {
+      "epoch": 2.1843003412969284,
+      "grad_norm": 0.22180932760238647,
+      "learning_rate": 2.0417271373784403e-06,
+      "loss": 0.0559,
+      "step": 373
+    },
+    {
+      "epoch": 2.1901511457825453,
+      "grad_norm": 0.21485093235969543,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.0444,
+      "step": 374
+    },
+    {
+      "epoch": 2.196001950268162,
+      "grad_norm": 0.21097077429294586,
+      "learning_rate": 1.9868268181037186e-06,
+      "loss": 0.0479,
+      "step": 375
+    },
+    {
+      "epoch": 2.2018527547537787,
+      "grad_norm": 0.2308683693408966,
+      "learning_rate": 1.9595877498858175e-06,
+      "loss": 0.0521,
+      "step": 376
+    },
+    {
+      "epoch": 2.2077035592393957,
+      "grad_norm": 0.21699382364749908,
+      "learning_rate": 1.9324911128742406e-06,
+      "loss": 0.0479,
+      "step": 377
+    },
+    {
+      "epoch": 2.213554363725012,
+      "grad_norm": 0.20137636363506317,
+      "learning_rate": 1.9055381764385272e-06,
+      "loss": 0.0507,
+      "step": 378
+    },
+    {
+      "epoch": 2.219405168210629,
+      "grad_norm": 0.227940171957016,
+      "learning_rate": 1.8787302032164168e-06,
+      "loss": 0.0568,
+      "step": 379
+    },
+    {
+      "epoch": 2.2252559726962455,
+      "grad_norm": 0.23801080882549286,
+      "learning_rate": 1.8520684490547014e-06,
+      "loss": 0.0582,
+      "step": 380
+    },
+    {
+      "epoch": 2.2311067771818625,
+      "grad_norm": 0.24348334968090057,
+      "learning_rate": 1.8255541629503865e-06,
+      "loss": 0.0505,
+      "step": 381
+    },
+    {
+      "epoch": 2.2369575816674794,
+      "grad_norm": 0.23667719960212708,
+      "learning_rate": 1.7991885869921928e-06,
+      "loss": 0.0423,
+      "step": 382
+    },
+    {
+      "epoch": 2.242808386153096,
+      "grad_norm": 0.21500073373317719,
+      "learning_rate": 1.7729729563023613e-06,
+      "loss": 0.0478,
+      "step": 383
+    },
+    {
+      "epoch": 2.248659190638713,
+      "grad_norm": 0.18407940864562988,
+      "learning_rate": 1.746908498978791e-06,
+      "loss": 0.0454,
+      "step": 384
+    },
+    {
+      "epoch": 2.2545099951243297,
+      "grad_norm": 0.22536802291870117,
+      "learning_rate": 1.7209964360375137e-06,
+      "loss": 0.0474,
+      "step": 385
+    },
+    {
+      "epoch": 2.260360799609946,
+      "grad_norm": 0.22089789807796478,
+      "learning_rate": 1.6952379813554914e-06,
+      "loss": 0.0407,
+      "step": 386
+    },
+    {
+      "epoch": 2.266211604095563,
+      "grad_norm": 0.19465979933738708,
+      "learning_rate": 1.6696343416137495e-06,
+      "loss": 0.05,
+      "step": 387
+    },
+    {
+      "epoch": 2.27206240858118,
+      "grad_norm": 0.2152717262506485,
+      "learning_rate": 1.6441867162408514e-06,
+      "loss": 0.0484,
+      "step": 388
+    },
+    {
+      "epoch": 2.2779132130667965,
+      "grad_norm": 0.1996590495109558,
+      "learning_rate": 1.6188962973567068e-06,
+      "loss": 0.0463,
+      "step": 389
+    },
+    {
+      "epoch": 2.2837640175524134,
+      "grad_norm": 0.22818255424499512,
+      "learning_rate": 1.5937642697167288e-06,
+      "loss": 0.0509,
+      "step": 390
+    },
+    {
+      "epoch": 2.2896148220380304,
+      "grad_norm": 0.18348443508148193,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.0469,
+      "step": 391
+    },
+    {
+      "epoch": 2.295465626523647,
+      "grad_norm": 0.16341239213943481,
+      "learning_rate": 1.5439800900357765e-06,
+      "loss": 0.0408,
+      "step": 392
+    },
+    {
+      "epoch": 2.3013164310092638,
+      "grad_norm": 0.22039690613746643,
+      "learning_rate": 1.5193302701853674e-06,
+      "loss": 0.0457,
+      "step": 393
+    },
+    {
+      "epoch": 2.3071672354948807,
+      "grad_norm": 0.20820854604244232,
+      "learning_rate": 1.4948435058510036e-06,
+      "loss": 0.0404,
+      "step": 394
+    },
+    {
+      "epoch": 2.313018039980497,
+      "grad_norm": 0.6139259338378906,
+      "learning_rate": 1.4705209441400841e-06,
+      "loss": 0.0516,
+      "step": 395
+    },
+    {
+      "epoch": 2.318868844466114,
+      "grad_norm": 0.1655004769563675,
+      "learning_rate": 1.4463637244677648e-06,
+      "loss": 0.0419,
+      "step": 396
+    },
+    {
+      "epoch": 2.324719648951731,
+      "grad_norm": 0.20899701118469238,
+      "learning_rate": 1.422372978503589e-06,
+      "loss": 0.0488,
+      "step": 397
+    },
+    {
+      "epoch": 2.3305704534373475,
+      "grad_norm": 0.19723419845104218,
+      "learning_rate": 1.3985498301184685e-06,
+      "loss": 0.048,
+      "step": 398
+    },
+    {
+      "epoch": 2.3364212579229644,
+      "grad_norm": 0.21295493841171265,
+      "learning_rate": 1.374895395332037e-06,
+      "loss": 0.0499,
+      "step": 399
+    },
+    {
+      "epoch": 2.3422720624085813,
+      "grad_norm": 0.22390897572040558,
+      "learning_rate": 1.351410782260366e-06,
+      "loss": 0.0501,
+      "step": 400
+    },
+    {
+      "epoch": 2.348122866894198,
+      "grad_norm": 0.22746333479881287,
+      "learning_rate": 1.3280970910640573e-06,
+      "loss": 0.0487,
+      "step": 401
+    },
+    {
+      "epoch": 2.3539736713798147,
+      "grad_norm": 0.20877297222614288,
+      "learning_rate": 1.3049554138967052e-06,
+      "loss": 0.043,
+      "step": 402
+    },
+    {
+      "epoch": 2.3598244758654316,
+      "grad_norm": 0.23040781915187836,
+      "learning_rate": 1.2819868348537263e-06,
+      "loss": 0.0521,
+      "step": 403
+    },
+    {
+      "epoch": 2.365675280351048,
+      "grad_norm": 0.18759937584400177,
+      "learning_rate": 1.259192429921584e-06,
+      "loss": 0.0411,
+      "step": 404
+    },
+    {
+      "epoch": 2.371526084836665,
+      "grad_norm": 0.21358315646648407,
+      "learning_rate": 1.2365732669273778e-06,
+      "loss": 0.0476,
+      "step": 405
+    },
+    {
+      "epoch": 2.377376889322282,
+      "grad_norm": 0.20594115555286407,
+      "learning_rate": 1.2141304054888204e-06,
+      "loss": 0.0501,
+      "step": 406
+    },
+    {
+      "epoch": 2.3832276938078985,
+      "grad_norm": 0.21114301681518555,
+      "learning_rate": 1.1918648969645947e-06,
+      "loss": 0.0427,
+      "step": 407
+    },
+    {
+      "epoch": 2.3890784982935154,
+      "grad_norm": 0.19082777202129364,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.0467,
+      "step": 408
+    },
+    {
+      "epoch": 2.3949293027791323,
+      "grad_norm": 0.19006142020225525,
+      "learning_rate": 1.1478701025036359e-06,
+      "loss": 0.0429,
+      "step": 409
+    },
+    {
+      "epoch": 2.4007801072647488,
+      "grad_norm": 0.22013723850250244,
+      "learning_rate": 1.126142877547826e-06,
+      "loss": 0.0481,
+      "step": 410
+    },
+    {
+      "epoch": 2.4066309117503657,
+      "grad_norm": 0.22271747887134552,
+      "learning_rate": 1.1045971273716476e-06,
+      "loss": 0.0538,
+      "step": 411
+    },
+    {
+      "epoch": 2.4124817162359826,
+      "grad_norm": 0.2010895311832428,
+      "learning_rate": 1.083233861307697e-06,
+      "loss": 0.0435,
+      "step": 412
+    },
+    {
+      "epoch": 2.418332520721599,
+      "grad_norm": 0.2763868272304535,
+      "learning_rate": 1.062054080139916e-06,
+      "loss": 0.0498,
+      "step": 413
+    },
+    {
+      "epoch": 2.424183325207216,
+      "grad_norm": 0.21242615580558777,
+      "learning_rate": 1.0410587760567104e-06,
+      "loss": 0.0533,
+      "step": 414
+    },
+    {
+      "epoch": 2.430034129692833,
+      "grad_norm": 0.24994240701198578,
+      "learning_rate": 1.0202489326044663e-06,
+      "loss": 0.0443,
+      "step": 415
+    },
+    {
+      "epoch": 2.4358849341784494,
+      "grad_norm": 0.26131340861320496,
+      "learning_rate": 9.99625524641481e-07,
+      "loss": 0.0465,
+      "step": 416
+    },
+    {
+      "epoch": 2.4417357386640663,
+      "grad_norm": 0.21973882615566254,
+      "learning_rate": 9.791895182922911e-07,
+      "loss": 0.0525,
+      "step": 417
+    },
+    {
+      "epoch": 2.4475865431496833,
+      "grad_norm": 0.21667824685573578,
+      "learning_rate": 9.589418709024146e-07,
+      "loss": 0.0435,
+      "step": 418
+    },
+    {
+      "epoch": 2.4534373476352997,
+      "grad_norm": 0.22149190306663513,
+      "learning_rate": 9.388835309934985e-07,
+      "loss": 0.0531,
+      "step": 419
+    },
+    {
+      "epoch": 2.4592881521209167,
+      "grad_norm": 0.2104058861732483,
+      "learning_rate": 9.190154382188921e-07,
+      "loss": 0.0518,
+      "step": 420
+    },
+    {
+      "epoch": 2.465138956606533,
+      "grad_norm": 0.19894002377986908,
+      "learning_rate": 8.993385233196223e-07,
+      "loss": 0.0432,
+      "step": 421
+    },
+    {
+      "epoch": 2.47098976109215,
+      "grad_norm": 0.2094515860080719,
+      "learning_rate": 8.79853708080795e-07,
+      "loss": 0.0528,
+      "step": 422
+    },
+    {
+      "epoch": 2.476840565577767,
+      "grad_norm": 0.5233778357505798,
+      "learning_rate": 8.605619052884106e-07,
+      "loss": 0.0445,
+      "step": 423
+    },
+    {
+      "epoch": 2.4826913700633835,
+      "grad_norm": 0.21081270277500153,
+      "learning_rate": 8.414640186866063e-07,
+      "loss": 0.0553,
+      "step": 424
+    },
+    {
+      "epoch": 2.4885421745490004,
+      "grad_norm": 0.1904570311307907,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.0389,
+      "step": 425
+    },
+    {
+      "epoch": 2.4943929790346173,
+      "grad_norm": 0.2278057038784027,
+      "learning_rate": 8.03853563568367e-07,
+      "loss": 0.0468,
+      "step": 426
+    },
+    {
+      "epoch": 2.500243783520234,
+      "grad_norm": 0.23266924917697906,
+      "learning_rate": 7.8534275695198e-07,
+      "loss": 0.0545,
+      "step": 427
+    },
+    {
+      "epoch": 2.5060945880058507,
+      "grad_norm": 0.23620003461837769,
+      "learning_rate": 7.670293902437331e-07,
+      "loss": 0.0502,
+      "step": 428
+    },
+    {
+      "epoch": 2.5119453924914676,
+      "grad_norm": 0.2107357382774353,
+      "learning_rate": 7.489143213519301e-07,
+      "loss": 0.0502,
+      "step": 429
+    },
+    {
+      "epoch": 2.517796196977084,
+      "grad_norm": 0.20279434323310852,
+      "learning_rate": 7.309983988954078e-07,
+      "loss": 0.0561,
+      "step": 430
+    },
+    {
+      "epoch": 2.523647001462701,
+      "grad_norm": 0.19296404719352722,
+      "learning_rate": 7.132824621637891e-07,
+      "loss": 0.0427,
+      "step": 431
+    },
+    {
+      "epoch": 2.529497805948318,
+      "grad_norm": 0.22379833459854126,
+      "learning_rate": 6.957673410781617e-07,
+      "loss": 0.0442,
+      "step": 432
+    },
+    {
+      "epoch": 2.5353486104339344,
+      "grad_norm": 0.20516741275787354,
+      "learning_rate": 6.784538561521986e-07,
+      "loss": 0.043,
+      "step": 433
+    },
+    {
+      "epoch": 2.5411994149195514,
+      "grad_norm": 0.20625388622283936,
+      "learning_rate": 6.613428184537235e-07,
+      "loss": 0.0555,
+      "step": 434
+    },
+    {
+      "epoch": 2.5470502194051683,
+      "grad_norm": 0.1993888020515442,
+      "learning_rate": 6.444350295667112e-07,
+      "loss": 0.0462,
+      "step": 435
+    },
+    {
+      "epoch": 2.5529010238907848,
+      "grad_norm": 0.20914866030216217,
+      "learning_rate": 6.277312815537423e-07,
+      "loss": 0.0449,
+      "step": 436
+    },
+    {
+      "epoch": 2.5587518283764017,
+      "grad_norm": 0.20487205684185028,
+      "learning_rate": 6.112323569188927e-07,
+      "loss": 0.0442,
+      "step": 437
+    },
+    {
+      "epoch": 2.5646026328620186,
+      "grad_norm": 0.2008737027645111,
+      "learning_rate": 5.949390285710777e-07,
+      "loss": 0.0454,
+      "step": 438
+    },
+    {
+      "epoch": 2.570453437347635,
+      "grad_norm": 0.20572151243686676,
+      "learning_rate": 5.788520597878477e-07,
+      "loss": 0.044,
+      "step": 439
+    },
+    {
+      "epoch": 2.576304241833252,
+      "grad_norm": 0.20191822946071625,
+      "learning_rate": 5.629722041796292e-07,
+      "loss": 0.0419,
+      "step": 440
+    },
+    {
+      "epoch": 2.582155046318869,
+      "grad_norm": 0.21377748250961304,
+      "learning_rate": 5.473002056544191e-07,
+      "loss": 0.045,
+      "step": 441
+    },
+    {
+      "epoch": 2.5880058508044854,
+      "grad_norm": 0.2058108150959015,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.0423,
+      "step": 442
+    },
+    {
+      "epoch": 2.5938566552901023,
+      "grad_norm": 0.20492474734783173,
+      "learning_rate": 5.165827067642415e-07,
+      "loss": 0.0473,
+      "step": 443
+    },
+    {
+      "epoch": 2.5997074597757193,
+      "grad_norm": 0.22236965596675873,
+      "learning_rate": 5.015386453917742e-07,
+      "loss": 0.04,
+      "step": 444
+    },
+    {
+      "epoch": 2.6055582642613357,
+      "grad_norm": 0.20536741614341736,
+      "learning_rate": 4.867053190199011e-07,
+      "loss": 0.0464,
+      "step": 445
+    },
+    {
+      "epoch": 2.6114090687469527,
+      "grad_norm": 0.2184278517961502,
+      "learning_rate": 4.720834225308962e-07,
+      "loss": 0.0508,
+      "step": 446
+    },
+    {
+      "epoch": 2.6172598732325696,
+      "grad_norm": 0.19578547775745392,
+      "learning_rate": 4.576736409023813e-07,
+      "loss": 0.0492,
+      "step": 447
+    },
+    {
+      "epoch": 2.623110677718186,
+      "grad_norm": 0.21041178703308105,
+      "learning_rate": 4.4347664917524293e-07,
+      "loss": 0.0467,
+      "step": 448
+    },
+    {
+      "epoch": 2.628961482203803,
+      "grad_norm": 0.19261011481285095,
+      "learning_rate": 4.29493112422007e-07,
+      "loss": 0.0519,
+      "step": 449
+    },
+    {
+      "epoch": 2.63481228668942,
+      "grad_norm": 0.1865607649087906,
+      "learning_rate": 4.15723685715686e-07,
+      "loss": 0.0452,
+      "step": 450
+    },
+    {
+      "epoch": 2.6406630911750364,
+      "grad_norm": 0.2131820172071457,
+      "learning_rate": 4.0216901409908695e-07,
+      "loss": 0.0434,
+      "step": 451
+    },
+    {
+      "epoch": 2.6465138956606533,
+      "grad_norm": 0.17361226677894592,
+      "learning_rate": 3.8882973255459975e-07,
+      "loss": 0.0373,
+      "step": 452
+    },
+    {
+      "epoch": 2.6523647001462702,
+      "grad_norm": 0.2203158587217331,
+      "learning_rate": 3.7570646597444196e-07,
+      "loss": 0.0432,
+      "step": 453
+    },
+    {
+      "epoch": 2.6582155046318867,
+      "grad_norm": 0.20222148299217224,
+      "learning_rate": 3.627998291313939e-07,
+      "loss": 0.0426,
+      "step": 454
+    },
+    {
+      "epoch": 2.6640663091175036,
+      "grad_norm": 0.20766018331050873,
+      "learning_rate": 3.5011042664999663e-07,
+      "loss": 0.0543,
+      "step": 455
+    },
+    {
+      "epoch": 2.6699171136031206,
+      "grad_norm": 0.22400252521038055,
+      "learning_rate": 3.3763885297822153e-07,
+      "loss": 0.0511,
+      "step": 456
+    },
+    {
+      "epoch": 2.675767918088737,
+      "grad_norm": 0.18321222066879272,
+      "learning_rate": 3.2538569235963216e-07,
+      "loss": 0.0459,
+      "step": 457
+    },
+    {
+      "epoch": 2.681618722574354,
+      "grad_norm": 0.18486328423023224,
+      "learning_rate": 3.133515188060077e-07,
+      "loss": 0.0429,
+      "step": 458
+    },
+    {
+      "epoch": 2.687469527059971,
+      "grad_norm": 0.20323659479618073,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.0469,
+      "step": 459
+    },
+    {
+      "epoch": 2.6933203315455874,
+      "grad_norm": 0.21503138542175293,
+      "learning_rate": 2.899423776210092e-07,
+      "loss": 0.0518,
+      "step": 460
+    },
+    {
+      "epoch": 2.6991711360312043,
+      "grad_norm": 0.2213236689567566,
+      "learning_rate": 2.785685066146776e-07,
+      "loss": 0.0547,
+      "step": 461
+    },
+    {
+      "epoch": 2.705021940516821,
+      "grad_norm": 0.20127376914024353,
+      "learning_rate": 2.6741581587202747e-07,
+      "loss": 0.0431,
+      "step": 462
+    },
+    {
+      "epoch": 2.7108727450024377,
+      "grad_norm": 0.37414053082466125,
+      "learning_rate": 2.5648482785220865e-07,
+      "loss": 0.0541,
+      "step": 463
+    },
+    {
+      "epoch": 2.7167235494880546,
+      "grad_norm": 0.21136891841888428,
+      "learning_rate": 2.4577605462847764e-07,
+      "loss": 0.0451,
+      "step": 464
+    },
+    {
+      "epoch": 2.7225743539736715,
+      "grad_norm": 0.1917283684015274,
+      "learning_rate": 2.3528999786421758e-07,
+      "loss": 0.0432,
+      "step": 465
+    },
+    {
+      "epoch": 2.728425158459288,
+      "grad_norm": 0.2059125304222107,
+      "learning_rate": 2.25027148789429e-07,
+      "loss": 0.0498,
+      "step": 466
+    },
+    {
+      "epoch": 2.734275962944905,
+      "grad_norm": 0.22194840013980865,
+      "learning_rate": 2.1498798817772281e-07,
+      "loss": 0.0484,
+      "step": 467
+    },
+    {
+      "epoch": 2.740126767430522,
+      "grad_norm": 0.2024865299463272,
+      "learning_rate": 2.0517298632379445e-07,
+      "loss": 0.0478,
+      "step": 468
+    },
+    {
+      "epoch": 2.7459775719161383,
+      "grad_norm": 0.2053341269493103,
+      "learning_rate": 1.9558260302139642e-07,
+      "loss": 0.044,
+      "step": 469
+    },
+    {
+      "epoch": 2.7518283764017553,
+      "grad_norm": 0.16805504262447357,
+      "learning_rate": 1.8621728754179392e-07,
+      "loss": 0.0435,
+      "step": 470
+    },
+    {
+      "epoch": 2.757679180887372,
+      "grad_norm": 0.22590601444244385,
+      "learning_rate": 1.770774786127244e-07,
+      "loss": 0.0442,
+      "step": 471
+    },
+    {
+      "epoch": 2.7635299853729887,
+      "grad_norm": 0.19346405565738678,
+      "learning_rate": 1.6816360439783797e-07,
+      "loss": 0.0454,
+      "step": 472
+    },
+    {
+      "epoch": 2.7693807898586056,
+      "grad_norm": 0.2147025167942047,
+      "learning_rate": 1.5947608247664558e-07,
+      "loss": 0.0469,
+      "step": 473
+    },
+    {
+      "epoch": 2.7752315943442225,
+      "grad_norm": 0.19654686748981476,
+      "learning_rate": 1.510153198249531e-07,
+      "loss": 0.046,
+      "step": 474
+    },
+    {
+      "epoch": 2.781082398829839,
+      "grad_norm": 0.1899406611919403,
+      "learning_rate": 1.4278171279579757e-07,
+      "loss": 0.0422,
+      "step": 475
+    },
+    {
+      "epoch": 2.786933203315456,
+      "grad_norm": 0.20060855150222778,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.0493,
+      "step": 476
+    },
+    {
+      "epoch": 2.792784007801073,
+      "grad_norm": 0.20946356654167175,
+      "learning_rate": 1.2699749779249926e-07,
+      "loss": 0.0491,
+      "step": 477
+    },
+    {
+      "epoch": 2.7986348122866893,
+      "grad_norm": 0.21608950197696686,
+      "learning_rate": 1.1944762924597286e-07,
+      "loss": 0.0501,
+      "step": 478
+    },
+    {
+      "epoch": 2.8044856167723062,
+      "grad_norm": 0.2118510901927948,
+      "learning_rate": 1.1212639514257829e-07,
+      "loss": 0.0491,
+      "step": 479
+    },
+    {
+      "epoch": 2.810336421257923,
+      "grad_norm": 0.19921454787254333,
+      "learning_rate": 1.0503413845297739e-07,
+      "loss": 0.0446,
+      "step": 480
+    },
+    {
+      "epoch": 2.8161872257435396,
+      "grad_norm": 0.2002425491809845,
+      "learning_rate": 9.817119142115472e-08,
+      "loss": 0.0469,
+      "step": 481
+    },
+    {
+      "epoch": 2.8220380302291566,
+      "grad_norm": 0.18556718528270721,
+      "learning_rate": 9.15378755488483e-08,
+      "loss": 0.0542,
+      "step": 482
+    },
+    {
+      "epoch": 2.8278888347147735,
+      "grad_norm": 0.2261078804731369,
+      "learning_rate": 8.513450158049109e-08,
+      "loss": 0.0513,
+      "step": 483
+    },
+    {
+      "epoch": 2.83373963920039,
+      "grad_norm": 0.18545158207416534,
+      "learning_rate": 7.896136948865429e-08,
+      "loss": 0.0483,
+      "step": 484
+    },
+    {
+      "epoch": 2.839590443686007,
+      "grad_norm": 0.21641848981380463,
+      "learning_rate": 7.301876845999368e-08,
+      "loss": 0.0504,
+      "step": 485
+    },
+    {
+      "epoch": 2.845441248171624,
+      "grad_norm": 0.1922488510608673,
+      "learning_rate": 6.730697688170251e-08,
+      "loss": 0.0491,
+      "step": 486
+    },
+    {
+      "epoch": 2.8512920526572403,
+      "grad_norm": 0.21676276624202728,
+      "learning_rate": 6.182626232847044e-08,
+      "loss": 0.045,
+      "step": 487
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.20930063724517822,
+      "learning_rate": 5.6576881549949e-08,
+      "loss": 0.0455,
+      "step": 488
+    },
+    {
+      "epoch": 2.862993661628474,
+      "grad_norm": 0.1886722296476364,
+      "learning_rate": 5.155908045872349e-08,
+      "loss": 0.0418,
+      "step": 489
+    },
+    {
+      "epoch": 2.8688444661140906,
+      "grad_norm": 0.19664409756660461,
+      "learning_rate": 4.677309411879327e-08,
+      "loss": 0.0458,
+      "step": 490
+    },
+    {
+      "epoch": 2.8746952705997075,
+      "grad_norm": 0.20216220617294312,
+      "learning_rate": 4.221914673455896e-08,
+      "loss": 0.0458,
+      "step": 491
+    },
+    {
+      "epoch": 2.8805460750853245,
+      "grad_norm": 0.18322984874248505,
+      "learning_rate": 3.7897451640321326e-08,
+      "loss": 0.045,
+      "step": 492
+    },
+    {
+      "epoch": 2.886396879570941,
+      "grad_norm": 0.21675418317317963,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.0506,
+      "step": 493
+    },
+    {
+      "epoch": 2.892247684056558,
+      "grad_norm": 0.21793396770954132,
+      "learning_rate": 2.995161724907658e-08,
+      "loss": 0.0449,
+      "step": 494
+    },
+    {
+      "epoch": 2.8980984885421748,
+      "grad_norm": 0.2188396006822586,
+      "learning_rate": 2.6327850182769065e-08,
+      "loss": 0.055,
+      "step": 495
+    },
+    {
+      "epoch": 2.9039492930277913,
+      "grad_norm": 0.2312510460615158,
+      "learning_rate": 2.29370798504186e-08,
+      "loss": 0.0449,
+      "step": 496
+    },
+    {
+      "epoch": 2.909800097513408,
+      "grad_norm": 0.22981475293636322,
+      "learning_rate": 1.9779465096112505e-08,
+      "loss": 0.0516,
+      "step": 497
+    },
+    {
+      "epoch": 2.915650901999025,
+      "grad_norm": 0.2100413292646408,
+      "learning_rate": 1.6855153841527915e-08,
+      "loss": 0.0425,
+      "step": 498
+    },
+    {
+      "epoch": 2.9215017064846416,
+      "grad_norm": 0.21841102838516235,
+      "learning_rate": 1.4164283079001196e-08,
+      "loss": 0.0558,
+      "step": 499
+    },
+    {
+      "epoch": 2.9273525109702585,
+      "grad_norm": 0.18299135565757751,
+      "learning_rate": 1.1706978865113072e-08,
+      "loss": 0.0416,
+      "step": 500
+    },
+    {
+      "epoch": 2.9332033154558754,
+      "grad_norm": 0.19131526350975037,
+      "learning_rate": 9.48335631477948e-09,
+      "loss": 0.042,
+      "step": 501
+    },
+    {
+      "epoch": 2.939054119941492,
+      "grad_norm": 0.1995655596256256,
+      "learning_rate": 7.49351959586253e-09,
+      "loss": 0.0621,
+      "step": 502
+    },
+    {
+      "epoch": 2.944904924427109,
+      "grad_norm": 0.18701446056365967,
+      "learning_rate": 5.737561924288315e-09,
+      "loss": 0.0392,
+      "step": 503
+    },
+    {
+      "epoch": 2.9507557289127258,
+      "grad_norm": 0.21277514100074768,
+      "learning_rate": 4.2155655596809455e-09,
+      "loss": 0.0484,
+      "step": 504
+    },
+    {
+      "epoch": 2.9566065333983422,
+      "grad_norm": 0.19108496606349945,
+      "learning_rate": 2.9276018015089725e-09,
+      "loss": 0.0486,
+      "step": 505
+    },
+    {
+      "epoch": 2.962457337883959,
+      "grad_norm": 0.2005542814731598,
+      "learning_rate": 1.8737309857463916e-09,
+      "loss": 0.0558,
+      "step": 506
+    },
+    {
+      "epoch": 2.968308142369576,
+      "grad_norm": 0.1871800273656845,
+      "learning_rate": 1.054002482043237e-09,
+      "loss": 0.0544,
+      "step": 507
+    },
+    {
+      "epoch": 2.9741589468551926,
+      "grad_norm": 0.21848636865615845,
+      "learning_rate": 4.684546914163201e-10,
+      "loss": 0.0513,
+      "step": 508
+    },
+    {
+      "epoch": 2.9800097513408095,
+      "grad_norm": 0.1974973976612091,
+      "learning_rate": 1.1711504444733567e-10,
+      "loss": 0.0431,
+      "step": 509
+    },
+    {
+      "epoch": 2.9858605558264264,
+      "grad_norm": 0.20914912223815918,
+      "learning_rate": 0.0,
+      "loss": 0.0556,
+      "step": 510
+    },
+    {
+      "epoch": 2.9858605558264264,
+      "step": 510,
+      "total_flos": 1495659198021632.0,
+      "train_loss": 0.09055571391740266,
+      "train_runtime": 153095.38,
+      "train_samples_per_second": 0.321,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1495659198021632.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b101651e72de96330d24f74536057d0eee0c1d820d853fde4cc3cedde2baf8dd
+size 7416