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/Qwen2.5-32B-Instruct
+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/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) 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": 2.9892735251097027,
+    "total_flos": 1494941780148224.0,
+    "train_loss": 0.029626486676872944,
+    "train_runtime": 67167.8945,
+    "train_samples_per_second": 0.733,
+    "train_steps_per_second": 0.008
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "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": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "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 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "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 sha256:9a508646f2416c107affa2565ae4338b65c06346fd0ca77fd2f549692e107817
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cee9ca0f2064367e1372c344c0bd3f65bfbf5840065aeedcff7f8ec03ec92ca
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91532a53694ba0a04178e012b67696aaaeabfbd98ee9399ddb4ae74fcfa1c1a6
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8742c1f09702e874aaeea52f35b91d59ef3955f61ea1b415070d58fb09162184
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30bc9b8c48c81931480cfd3d797e779e75f727720bf129a26bd22375241cbb29
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de1ab4637f40fe23ec5195f12ae9719b237f1dee5070af2558e9198517598f6
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f893d42883bcb94b8630ac1952a49d3de259408924b9b90aee2624651e0896b7
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92ec03df7b2404286f788a713a218307d1b1498cef0f2482bb4c038a83ca6ba
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28e4d633d376b719693a03c64a0420ff85d6c3651eab680f878620cd509de31
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291635ac7fd91e2f30fa9cb3cd4f7378a6e610cb242b0dae26f4581133eb67ed
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3006b91e470bb470ea41c1df1acdc4095e8d4e586bb8fcb9952b89a3f9ecc21
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2a8432f9c756dca12471f1b2cfc38b31f38fbb20661ba6f176c442f9b33af1
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc629b8fdd8770d9faa65cadbf0881cf2d3480fdf66f97c74e90d2d9e8979c2
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ffe89489ca17850d82562550cd5faf1a9045d9f02c1f5b15c6163f65482aee
+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 Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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 Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9892735251097027,
+    "total_flos": 1494941780148224.0,
+    "train_loss": 0.029626486676872944,
+    "train_runtime": 67167.8945,
+    "train_samples_per_second": 0.733,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,3612 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9892735251097027,
+  "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": 2.4042019844055176,
+      "learning_rate": 1.9607843137254904e-07,
+      "loss": 0.4984,
+      "step": 1
+    },
+    {
+      "epoch": 0.011701608971233545,
+      "grad_norm": 2.46307110786438,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 0.5004,
+      "step": 2
+    },
+    {
+      "epoch": 0.017552413456850317,
+      "grad_norm": 2.4179155826568604,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.5124,
+      "step": 3
+    },
+    {
+      "epoch": 0.02340321794246709,
+      "grad_norm": 2.3512749671936035,
+      "learning_rate": 7.843137254901962e-07,
+      "loss": 0.4679,
+      "step": 4
+    },
+    {
+      "epoch": 0.02925402242808386,
+      "grad_norm": 2.3498940467834473,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.513,
+      "step": 5
+    },
+    {
+      "epoch": 0.035104826913700635,
+      "grad_norm": 2.35388445854187,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.506,
+      "step": 6
+    },
+    {
+      "epoch": 0.040955631399317405,
+      "grad_norm": 2.130160093307495,
+      "learning_rate": 1.3725490196078434e-06,
+      "loss": 0.481,
+      "step": 7
+    },
+    {
+      "epoch": 0.04680643588493418,
+      "grad_norm": 1.7983100414276123,
+      "learning_rate": 1.5686274509803923e-06,
+      "loss": 0.4636,
+      "step": 8
+    },
+    {
+      "epoch": 0.05265724037055095,
+      "grad_norm": 1.7637169361114502,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.4812,
+      "step": 9
+    },
+    {
+      "epoch": 0.05850804485616772,
+      "grad_norm": 1.7297167778015137,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.4754,
+      "step": 10
+    },
+    {
+      "epoch": 0.0643588493417845,
+      "grad_norm": 1.4557020664215088,
+      "learning_rate": 2.1568627450980393e-06,
+      "loss": 0.4483,
+      "step": 11
+    },
+    {
+      "epoch": 0.07020965382740127,
+      "grad_norm": 1.4000929594039917,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.4637,
+      "step": 12
+    },
+    {
+      "epoch": 0.07606045831301804,
+      "grad_norm": 1.2742167711257935,
+      "learning_rate": 2.549019607843137e-06,
+      "loss": 0.4512,
+      "step": 13
+    },
+    {
+      "epoch": 0.08191126279863481,
+      "grad_norm": 0.9762641787528992,
+      "learning_rate": 2.7450980392156867e-06,
+      "loss": 0.4386,
+      "step": 14
+    },
+    {
+      "epoch": 0.08776206728425158,
+      "grad_norm": 0.8408783078193665,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.389,
+      "step": 15
+    },
+    {
+      "epoch": 0.09361287176986836,
+      "grad_norm": 0.8847479224205017,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 0.4037,
+      "step": 16
+    },
+    {
+      "epoch": 0.09946367625548513,
+      "grad_norm": 0.8736488223075867,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.4273,
+      "step": 17
+    },
+    {
+      "epoch": 0.1053144807411019,
+      "grad_norm": 0.7419383525848389,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.3898,
+      "step": 18
+    },
+    {
+      "epoch": 0.11116528522671867,
+      "grad_norm": 0.7293541431427002,
+      "learning_rate": 3.7254901960784316e-06,
+      "loss": 0.4233,
+      "step": 19
+    },
+    {
+      "epoch": 0.11701608971233544,
+      "grad_norm": 1.9727623462677002,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 0.3701,
+      "step": 20
+    },
+    {
+      "epoch": 0.12286689419795221,
+      "grad_norm": 0.915031373500824,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.3727,
+      "step": 21
+    },
+    {
+      "epoch": 0.128717698683569,
+      "grad_norm": 0.9051816463470459,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 0.3683,
+      "step": 22
+    },
+    {
+      "epoch": 0.13456850316918575,
+      "grad_norm": 0.7431566715240479,
+      "learning_rate": 4.509803921568628e-06,
+      "loss": 0.3567,
+      "step": 23
+    },
+    {
+      "epoch": 0.14041930765480254,
+      "grad_norm": 0.5959689021110535,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.342,
+      "step": 24
+    },
+    {
+      "epoch": 0.1462701121404193,
+      "grad_norm": 0.5637457966804504,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 0.3199,
+      "step": 25
+    },
+    {
+      "epoch": 0.15212091662603608,
+      "grad_norm": 0.5946214199066162,
+      "learning_rate": 5.098039215686274e-06,
+      "loss": 0.3299,
+      "step": 26
+    },
+    {
+      "epoch": 0.15797172111165286,
+      "grad_norm": 0.4843839108943939,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.3049,
+      "step": 27
+    },
+    {
+      "epoch": 0.16382252559726962,
+      "grad_norm": 0.49762770533561707,
+      "learning_rate": 5.4901960784313735e-06,
+      "loss": 0.2883,
+      "step": 28
+    },
+    {
+      "epoch": 0.1696733300828864,
+      "grad_norm": 0.5575108528137207,
+      "learning_rate": 5.686274509803922e-06,
+      "loss": 0.302,
+      "step": 29
+    },
+    {
+      "epoch": 0.17552413456850316,
+      "grad_norm": 0.5406191945075989,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.2851,
+      "step": 30
+    },
+    {
+      "epoch": 0.18137493905411994,
+      "grad_norm": 0.4934878945350647,
+      "learning_rate": 6.07843137254902e-06,
+      "loss": 0.2748,
+      "step": 31
+    },
+    {
+      "epoch": 0.18722574353973673,
+      "grad_norm": 0.5784087777137756,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 0.2993,
+      "step": 32
+    },
+    {
+      "epoch": 0.19307654802535348,
+      "grad_norm": 0.5021258592605591,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.276,
+      "step": 33
+    },
+    {
+      "epoch": 0.19892735251097027,
+      "grad_norm": 0.44409283995628357,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.2574,
+      "step": 34
+    },
+    {
+      "epoch": 0.20477815699658702,
+      "grad_norm": 0.4324759840965271,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.2427,
+      "step": 35
+    },
+    {
+      "epoch": 0.2106289614822038,
+      "grad_norm": 0.4134741425514221,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.2693,
+      "step": 36
+    },
+    {
+      "epoch": 0.21647976596782056,
+      "grad_norm": 0.3712354600429535,
+      "learning_rate": 7.2549019607843145e-06,
+      "loss": 0.2547,
+      "step": 37
+    },
+    {
+      "epoch": 0.22233057045343735,
+      "grad_norm": 0.3564675748348236,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 0.2189,
+      "step": 38
+    },
+    {
+      "epoch": 0.22818137493905413,
+      "grad_norm": 0.3792021572589874,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.2457,
+      "step": 39
+    },
+    {
+      "epoch": 0.2340321794246709,
+      "grad_norm": 0.39038991928100586,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.2488,
+      "step": 40
+    },
+    {
+      "epoch": 0.23988298391028767,
+      "grad_norm": 0.3869354724884033,
+      "learning_rate": 8.03921568627451e-06,
+      "loss": 0.2234,
+      "step": 41
+    },
+    {
+      "epoch": 0.24573378839590443,
+      "grad_norm": 0.44067057967185974,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.25,
+      "step": 42
+    },
+    {
+      "epoch": 0.2515845928815212,
+      "grad_norm": 0.34073254466056824,
+      "learning_rate": 8.43137254901961e-06,
+      "loss": 0.2214,
+      "step": 43
+    },
+    {
+      "epoch": 0.257435397367138,
+      "grad_norm": 0.3576607406139374,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 0.222,
+      "step": 44
+    },
+    {
+      "epoch": 0.26328620185275475,
+      "grad_norm": 0.3421995937824249,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.2023,
+      "step": 45
+    },
+    {
+      "epoch": 0.2691370063383715,
+      "grad_norm": 0.36221471428871155,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 0.2078,
+      "step": 46
+    },
+    {
+      "epoch": 0.2749878108239883,
+      "grad_norm": 0.3617911636829376,
+      "learning_rate": 9.215686274509804e-06,
+      "loss": 0.2067,
+      "step": 47
+    },
+    {
+      "epoch": 0.2808386153096051,
+      "grad_norm": 0.37211400270462036,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.1999,
+      "step": 48
+    },
+    {
+      "epoch": 0.28668941979522183,
+      "grad_norm": 0.3575108051300049,
+      "learning_rate": 9.607843137254903e-06,
+      "loss": 0.2098,
+      "step": 49
+    },
+    {
+      "epoch": 0.2925402242808386,
+      "grad_norm": 0.3736143112182617,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.2121,
+      "step": 50
+    },
+    {
+      "epoch": 0.2983910287664554,
+      "grad_norm": 0.3584408164024353,
+      "learning_rate": 1e-05,
+      "loss": 0.1986,
+      "step": 51
+    },
+    {
+      "epoch": 0.30424183325207216,
+      "grad_norm": 0.32740485668182373,
+      "learning_rate": 9.999882884955554e-06,
+      "loss": 0.1744,
+      "step": 52
+    },
+    {
+      "epoch": 0.3100926377376889,
+      "grad_norm": 0.3438873887062073,
+      "learning_rate": 9.999531545308584e-06,
+      "loss": 0.1955,
+      "step": 53
+    },
+    {
+      "epoch": 0.3159434422233057,
+      "grad_norm": 0.3557385206222534,
+      "learning_rate": 9.998945997517957e-06,
+      "loss": 0.1908,
+      "step": 54
+    },
+    {
+      "epoch": 0.3217942467089225,
+      "grad_norm": 0.3771747052669525,
+      "learning_rate": 9.998126269014255e-06,
+      "loss": 0.1933,
+      "step": 55
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.3500851094722748,
+      "learning_rate": 9.997072398198492e-06,
+      "loss": 0.1892,
+      "step": 56
+    },
+    {
+      "epoch": 0.333495855680156,
+      "grad_norm": 0.33903267979621887,
+      "learning_rate": 9.99578443444032e-06,
+      "loss": 0.1747,
+      "step": 57
+    },
+    {
+      "epoch": 0.3393466601657728,
+      "grad_norm": 0.3747689425945282,
+      "learning_rate": 9.994262438075713e-06,
+      "loss": 0.2007,
+      "step": 58
+    },
+    {
+      "epoch": 0.34519746465138956,
+      "grad_norm": 0.33843183517456055,
+      "learning_rate": 9.992506480404137e-06,
+      "loss": 0.1789,
+      "step": 59
+    },
+    {
+      "epoch": 0.3510482691370063,
+      "grad_norm": 0.49277859926223755,
+      "learning_rate": 9.990516643685222e-06,
+      "loss": 0.1799,
+      "step": 60
+    },
+    {
+      "epoch": 0.35689907362262313,
+      "grad_norm": 0.32874795794487,
+      "learning_rate": 9.988293021134888e-06,
+      "loss": 0.167,
+      "step": 61
+    },
+    {
+      "epoch": 0.3627498781082399,
+      "grad_norm": 0.3928215503692627,
+      "learning_rate": 9.985835716921e-06,
+      "loss": 0.1715,
+      "step": 62
+    },
+    {
+      "epoch": 0.36860068259385664,
+      "grad_norm": 0.36052584648132324,
+      "learning_rate": 9.983144846158472e-06,
+      "loss": 0.1785,
+      "step": 63
+    },
+    {
+      "epoch": 0.37445148707947346,
+      "grad_norm": 0.33686086535453796,
+      "learning_rate": 9.980220534903889e-06,
+      "loss": 0.1747,
+      "step": 64
+    },
+    {
+      "epoch": 0.3803022915650902,
+      "grad_norm": 0.36128610372543335,
+      "learning_rate": 9.977062920149583e-06,
+      "loss": 0.1773,
+      "step": 65
+    },
+    {
+      "epoch": 0.38615309605070697,
+      "grad_norm": 0.3438204824924469,
+      "learning_rate": 9.973672149817232e-06,
+      "loss": 0.1595,
+      "step": 66
+    },
+    {
+      "epoch": 0.3920039005363237,
+      "grad_norm": 0.3195885419845581,
+      "learning_rate": 9.970048382750925e-06,
+      "loss": 0.1698,
+      "step": 67
+    },
+    {
+      "epoch": 0.39785470502194054,
+      "grad_norm": 0.3541395664215088,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.1732,
+      "step": 68
+    },
+    {
+      "epoch": 0.4037055095075573,
+      "grad_norm": 0.3797125816345215,
+      "learning_rate": 9.96210254835968e-06,
+      "loss": 0.1855,
+      "step": 69
+    },
+    {
+      "epoch": 0.40955631399317405,
+      "grad_norm": 0.4068518280982971,
+      "learning_rate": 9.957780853265441e-06,
+      "loss": 0.1803,
+      "step": 70
+    },
+    {
+      "epoch": 0.41540711847879086,
+      "grad_norm": 0.3230303227901459,
+      "learning_rate": 9.953226905881208e-06,
+      "loss": 0.1551,
+      "step": 71
+    },
+    {
+      "epoch": 0.4212579229644076,
+      "grad_norm": 0.3526642918586731,
+      "learning_rate": 9.948440919541277e-06,
+      "loss": 0.1659,
+      "step": 72
+    },
+    {
+      "epoch": 0.4271087274500244,
+      "grad_norm": 0.36039891839027405,
+      "learning_rate": 9.943423118450051e-06,
+      "loss": 0.1741,
+      "step": 73
+    },
+    {
+      "epoch": 0.43295953193564113,
+      "grad_norm": 0.4426978826522827,
+      "learning_rate": 9.938173737671531e-06,
+      "loss": 0.1747,
+      "step": 74
+    },
+    {
+      "epoch": 0.43881033642125794,
+      "grad_norm": 0.37956029176712036,
+      "learning_rate": 9.932693023118299e-06,
+      "loss": 0.1766,
+      "step": 75
+    },
+    {
+      "epoch": 0.4446611409068747,
+      "grad_norm": 0.3615328371524811,
+      "learning_rate": 9.926981231540007e-06,
+      "loss": 0.1775,
+      "step": 76
+    },
+    {
+      "epoch": 0.45051194539249145,
+      "grad_norm": 0.37767109274864197,
+      "learning_rate": 9.921038630511345e-06,
+      "loss": 0.1829,
+      "step": 77
+    },
+    {
+      "epoch": 0.45636274987810826,
+      "grad_norm": 0.35032397508621216,
+      "learning_rate": 9.91486549841951e-06,
+      "loss": 0.1714,
+      "step": 78
+    },
+    {
+      "epoch": 0.462213554363725,
+      "grad_norm": 0.41910672187805176,
+      "learning_rate": 9.908462124451152e-06,
+      "loss": 0.1716,
+      "step": 79
+    },
+    {
+      "epoch": 0.4680643588493418,
+      "grad_norm": 0.3652605414390564,
+      "learning_rate": 9.901828808578846e-06,
+      "loss": 0.1496,
+      "step": 80
+    },
+    {
+      "epoch": 0.47391516333495853,
+      "grad_norm": 0.40993812680244446,
+      "learning_rate": 9.894965861547023e-06,
+      "loss": 0.1633,
+      "step": 81
+    },
+    {
+      "epoch": 0.47976596782057535,
+      "grad_norm": 0.3730096220970154,
+      "learning_rate": 9.887873604857424e-06,
+      "loss": 0.1661,
+      "step": 82
+    },
+    {
+      "epoch": 0.4856167723061921,
+      "grad_norm": 0.36139336228370667,
+      "learning_rate": 9.88055237075403e-06,
+      "loss": 0.1677,
+      "step": 83
+    },
+    {
+      "epoch": 0.49146757679180886,
+      "grad_norm": 0.38538867235183716,
+      "learning_rate": 9.873002502207502e-06,
+      "loss": 0.1708,
+      "step": 84
+    },
+    {
+      "epoch": 0.49731838127742567,
+      "grad_norm": 0.38366183638572693,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.1742,
+      "step": 85
+    },
+    {
+      "epoch": 0.5031691857630424,
+      "grad_norm": 0.3716081380844116,
+      "learning_rate": 9.857218287204204e-06,
+      "loss": 0.1539,
+      "step": 86
+    },
+    {
+      "epoch": 0.5090199902486592,
+      "grad_norm": 0.40919578075408936,
+      "learning_rate": 9.848984680175049e-06,
+      "loss": 0.1774,
+      "step": 87
+    },
+    {
+      "epoch": 0.514870794734276,
+      "grad_norm": 0.3685464560985565,
+      "learning_rate": 9.840523917523354e-06,
+      "loss": 0.1686,
+      "step": 88
+    },
+    {
+      "epoch": 0.5207215992198927,
+      "grad_norm": 0.3441756069660187,
+      "learning_rate": 9.831836395602164e-06,
+      "loss": 0.1497,
+      "step": 89
+    },
+    {
+      "epoch": 0.5265724037055095,
+      "grad_norm": 0.3777903914451599,
+      "learning_rate": 9.822922521387277e-06,
+      "loss": 0.1615,
+      "step": 90
+    },
+    {
+      "epoch": 0.5324232081911263,
+      "grad_norm": 0.3399229347705841,
+      "learning_rate": 9.813782712458206e-06,
+      "loss": 0.1558,
+      "step": 91
+    },
+    {
+      "epoch": 0.538274012676743,
+      "grad_norm": 0.41103455424308777,
+      "learning_rate": 9.804417396978605e-06,
+      "loss": 0.1591,
+      "step": 92
+    },
+    {
+      "epoch": 0.5441248171623598,
+      "grad_norm": 0.4678979218006134,
+      "learning_rate": 9.794827013676206e-06,
+      "loss": 0.1793,
+      "step": 93
+    },
+    {
+      "epoch": 0.5499756216479766,
+      "grad_norm": 0.3981055021286011,
+      "learning_rate": 9.78501201182228e-06,
+      "loss": 0.1731,
+      "step": 94
+    },
+    {
+      "epoch": 0.5558264261335933,
+      "grad_norm": 0.3952052593231201,
+      "learning_rate": 9.774972851210572e-06,
+      "loss": 0.1687,
+      "step": 95
+    },
+    {
+      "epoch": 0.5616772306192102,
+      "grad_norm": 0.5214592218399048,
+      "learning_rate": 9.764710002135784e-06,
+      "loss": 0.1497,
+      "step": 96
+    },
+    {
+      "epoch": 0.567528035104827,
+      "grad_norm": 0.3616654872894287,
+      "learning_rate": 9.754223945371524e-06,
+      "loss": 0.1617,
+      "step": 97
+    },
+    {
+      "epoch": 0.5733788395904437,
+      "grad_norm": 0.37656962871551514,
+      "learning_rate": 9.743515172147793e-06,
+      "loss": 0.1533,
+      "step": 98
+    },
+    {
+      "epoch": 0.5792296440760605,
+      "grad_norm": 0.4490816593170166,
+      "learning_rate": 9.732584184127973e-06,
+      "loss": 0.1629,
+      "step": 99
+    },
+    {
+      "epoch": 0.5850804485616772,
+      "grad_norm": 0.3636768162250519,
+      "learning_rate": 9.721431493385322e-06,
+      "loss": 0.1493,
+      "step": 100
+    },
+    {
+      "epoch": 0.590931253047294,
+      "grad_norm": 0.3367384076118469,
+      "learning_rate": 9.710057622378992e-06,
+      "loss": 0.1582,
+      "step": 101
+    },
+    {
+      "epoch": 0.5967820575329108,
+      "grad_norm": 0.5017166137695312,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.1699,
+      "step": 102
+    },
+    {
+      "epoch": 0.6026328620185275,
+      "grad_norm": 0.3878183960914612,
+      "learning_rate": 9.686648481193994e-06,
+      "loss": 0.1646,
+      "step": 103
+    },
+    {
+      "epoch": 0.6084836665041443,
+      "grad_norm": 0.35837483406066895,
+      "learning_rate": 9.674614307640368e-06,
+      "loss": 0.1637,
+      "step": 104
+    },
+    {
+      "epoch": 0.6143344709897611,
+      "grad_norm": 0.41536927223205566,
+      "learning_rate": 9.66236114702178e-06,
+      "loss": 0.1634,
+      "step": 105
+    },
+    {
+      "epoch": 0.6201852754753778,
+      "grad_norm": 0.3885203003883362,
+      "learning_rate": 9.649889573350006e-06,
+      "loss": 0.1573,
+      "step": 106
+    },
+    {
+      "epoch": 0.6260360799609946,
+      "grad_norm": 0.3583751618862152,
+      "learning_rate": 9.637200170868607e-06,
+      "loss": 0.1372,
+      "step": 107
+    },
+    {
+      "epoch": 0.6318868844466115,
+      "grad_norm": 0.4037657678127289,
+      "learning_rate": 9.62429353402556e-06,
+      "loss": 0.1538,
+      "step": 108
+    },
+    {
+      "epoch": 0.6377376889322282,
+      "grad_norm": 0.35686999559402466,
+      "learning_rate": 9.611170267445401e-06,
+      "loss": 0.1572,
+      "step": 109
+    },
+    {
+      "epoch": 0.643588493417845,
+      "grad_norm": 0.37882205843925476,
+      "learning_rate": 9.597830985900913e-06,
+      "loss": 0.1516,
+      "step": 110
+    },
+    {
+      "epoch": 0.6494392979034618,
+      "grad_norm": 0.4156239330768585,
+      "learning_rate": 9.584276314284316e-06,
+      "loss": 0.1633,
+      "step": 111
+    },
+    {
+      "epoch": 0.6552901023890785,
+      "grad_norm": 0.41733554005622864,
+      "learning_rate": 9.570506887577994e-06,
+      "loss": 0.1555,
+      "step": 112
+    },
+    {
+      "epoch": 0.6611409068746953,
+      "grad_norm": 0.350704163312912,
+      "learning_rate": 9.556523350824759e-06,
+      "loss": 0.1417,
+      "step": 113
+    },
+    {
+      "epoch": 0.666991711360312,
+      "grad_norm": 0.4148392975330353,
+      "learning_rate": 9.542326359097619e-06,
+      "loss": 0.158,
+      "step": 114
+    },
+    {
+      "epoch": 0.6728425158459288,
+      "grad_norm": 0.40368494391441345,
+      "learning_rate": 9.527916577469104e-06,
+      "loss": 0.1599,
+      "step": 115
+    },
+    {
+      "epoch": 0.6786933203315456,
+      "grad_norm": 0.41338789463043213,
+      "learning_rate": 9.5132946809801e-06,
+      "loss": 0.1638,
+      "step": 116
+    },
+    {
+      "epoch": 0.6845441248171623,
+      "grad_norm": 0.3733426332473755,
+      "learning_rate": 9.498461354608228e-06,
+      "loss": 0.1471,
+      "step": 117
+    },
+    {
+      "epoch": 0.6903949293027791,
+      "grad_norm": 0.3726441264152527,
+      "learning_rate": 9.483417293235759e-06,
+      "loss": 0.1683,
+      "step": 118
+    },
+    {
+      "epoch": 0.6962457337883959,
+      "grad_norm": 0.375068724155426,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.1523,
+      "step": 119
+    },
+    {
+      "epoch": 0.7020965382740126,
+      "grad_norm": 0.3736395537853241,
+      "learning_rate": 9.452699794345583e-06,
+      "loss": 0.15,
+      "step": 120
+    },
+    {
+      "epoch": 0.7079473427596294,
+      "grad_norm": 0.37468886375427246,
+      "learning_rate": 9.437027795820373e-06,
+      "loss": 0.1598,
+      "step": 121
+    },
+    {
+      "epoch": 0.7137981472452463,
+      "grad_norm": 0.36749985814094543,
+      "learning_rate": 9.421147940212152e-06,
+      "loss": 0.1605,
+      "step": 122
+    },
+    {
+      "epoch": 0.719648951730863,
+      "grad_norm": 0.3597930669784546,
+      "learning_rate": 9.405060971428924e-06,
+      "loss": 0.149,
+      "step": 123
+    },
+    {
+      "epoch": 0.7254997562164798,
+      "grad_norm": 0.39379099011421204,
+      "learning_rate": 9.388767643081109e-06,
+      "loss": 0.159,
+      "step": 124
+    },
+    {
+      "epoch": 0.7313505607020966,
+      "grad_norm": 0.37788447737693787,
+      "learning_rate": 9.372268718446259e-06,
+      "loss": 0.1691,
+      "step": 125
+    },
+    {
+      "epoch": 0.7372013651877133,
+      "grad_norm": 0.3714412748813629,
+      "learning_rate": 9.355564970433288e-06,
+      "loss": 0.1571,
+      "step": 126
+    },
+    {
+      "epoch": 0.7430521696733301,
+      "grad_norm": 0.37507206201553345,
+      "learning_rate": 9.338657181546277e-06,
+      "loss": 0.1567,
+      "step": 127
+    },
+    {
+      "epoch": 0.7489029741589469,
+      "grad_norm": 0.34279665350914,
+      "learning_rate": 9.321546143847802e-06,
+      "loss": 0.1463,
+      "step": 128
+    },
+    {
+      "epoch": 0.7547537786445636,
+      "grad_norm": 0.4015829265117645,
+      "learning_rate": 9.30423265892184e-06,
+      "loss": 0.1604,
+      "step": 129
+    },
+    {
+      "epoch": 0.7606045831301804,
+      "grad_norm": 0.36534038186073303,
+      "learning_rate": 9.286717537836211e-06,
+      "loss": 0.1595,
+      "step": 130
+    },
+    {
+      "epoch": 0.7664553876157971,
+      "grad_norm": 0.35713326930999756,
+      "learning_rate": 9.269001601104593e-06,
+      "loss": 0.1641,
+      "step": 131
+    },
+    {
+      "epoch": 0.7723061921014139,
+      "grad_norm": 0.393284410238266,
+      "learning_rate": 9.251085678648072e-06,
+      "loss": 0.1625,
+      "step": 132
+    },
+    {
+      "epoch": 0.7781569965870307,
+      "grad_norm": 0.3619539141654968,
+      "learning_rate": 9.232970609756267e-06,
+      "loss": 0.1481,
+      "step": 133
+    },
+    {
+      "epoch": 0.7840078010726474,
+      "grad_norm": 0.35219714045524597,
+      "learning_rate": 9.214657243048021e-06,
+      "loss": 0.1494,
+      "step": 134
+    },
+    {
+      "epoch": 0.7898586055582643,
+      "grad_norm": 0.38188058137893677,
+      "learning_rate": 9.196146436431635e-06,
+      "loss": 0.161,
+      "step": 135
+    },
+    {
+      "epoch": 0.7957094100438811,
+      "grad_norm": 0.3557851314544678,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.1571,
+      "step": 136
+    },
+    {
+      "epoch": 0.8015602145294978,
+      "grad_norm": 0.3425387442111969,
+      "learning_rate": 9.158535981313395e-06,
+      "loss": 0.1429,
+      "step": 137
+    },
+    {
+      "epoch": 0.8074110190151146,
+      "grad_norm": 0.35848724842071533,
+      "learning_rate": 9.13943809471159e-06,
+      "loss": 0.1592,
+      "step": 138
+    },
+    {
+      "epoch": 0.8132618235007314,
+      "grad_norm": 0.3686351776123047,
+      "learning_rate": 9.120146291919206e-06,
+      "loss": 0.149,
+      "step": 139
+    },
+    {
+      "epoch": 0.8191126279863481,
+      "grad_norm": 0.3813227713108063,
+      "learning_rate": 9.100661476680379e-06,
+      "loss": 0.1503,
+      "step": 140
+    },
+    {
+      "epoch": 0.8249634324719649,
+      "grad_norm": 0.3804561495780945,
+      "learning_rate": 9.08098456178111e-06,
+      "loss": 0.1547,
+      "step": 141
+    },
+    {
+      "epoch": 0.8308142369575817,
+      "grad_norm": 0.3664409816265106,
+      "learning_rate": 9.061116469006504e-06,
+      "loss": 0.1555,
+      "step": 142
+    },
+    {
+      "epoch": 0.8366650414431984,
+      "grad_norm": 0.3414985239505768,
+      "learning_rate": 9.041058129097586e-06,
+      "loss": 0.1376,
+      "step": 143
+    },
+    {
+      "epoch": 0.8425158459288152,
+      "grad_norm": 0.3685246407985687,
+      "learning_rate": 9.020810481707709e-06,
+      "loss": 0.148,
+      "step": 144
+    },
+    {
+      "epoch": 0.8483666504144319,
+      "grad_norm": 0.3861325681209564,
+      "learning_rate": 9.00037447535852e-06,
+      "loss": 0.1649,
+      "step": 145
+    },
+    {
+      "epoch": 0.8542174549000487,
+      "grad_norm": 0.38169729709625244,
+      "learning_rate": 8.979751067395534e-06,
+      "loss": 0.1475,
+      "step": 146
+    },
+    {
+      "epoch": 0.8600682593856656,
+      "grad_norm": 0.39888978004455566,
+      "learning_rate": 8.958941223943292e-06,
+      "loss": 0.1673,
+      "step": 147
+    },
+    {
+      "epoch": 0.8659190638712823,
+      "grad_norm": 0.38037005066871643,
+      "learning_rate": 8.937945919860086e-06,
+      "loss": 0.1577,
+      "step": 148
+    },
+    {
+      "epoch": 0.8717698683568991,
+      "grad_norm": 0.37339454889297485,
+      "learning_rate": 8.916766138692303e-06,
+      "loss": 0.1581,
+      "step": 149
+    },
+    {
+      "epoch": 0.8776206728425159,
+      "grad_norm": 0.39251771569252014,
+      "learning_rate": 8.895402872628352e-06,
+      "loss": 0.1482,
+      "step": 150
+    },
+    {
+      "epoch": 0.8834714773281326,
+      "grad_norm": 0.33527621626853943,
+      "learning_rate": 8.873857122452174e-06,
+      "loss": 0.1361,
+      "step": 151
+    },
+    {
+      "epoch": 0.8893222818137494,
+      "grad_norm": 0.380577027797699,
+      "learning_rate": 8.852129897496367e-06,
+      "loss": 0.1495,
+      "step": 152
+    },
+    {
+      "epoch": 0.8951730862993662,
+      "grad_norm": 0.3689667284488678,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.1605,
+      "step": 153
+    },
+    {
+      "epoch": 0.9010238907849829,
+      "grad_norm": 0.39303916692733765,
+      "learning_rate": 8.808135103035407e-06,
+      "loss": 0.1472,
+      "step": 154
+    },
+    {
+      "epoch": 0.9068746952705997,
+      "grad_norm": 0.37502506375312805,
+      "learning_rate": 8.785869594511182e-06,
+      "loss": 0.1621,
+      "step": 155
+    },
+    {
+      "epoch": 0.9127254997562165,
+      "grad_norm": 0.3729185461997986,
+      "learning_rate": 8.763426733072624e-06,
+      "loss": 0.1538,
+      "step": 156
+    },
+    {
+      "epoch": 0.9185763042418332,
+      "grad_norm": 0.38975661993026733,
+      "learning_rate": 8.740807570078419e-06,
+      "loss": 0.165,
+      "step": 157
+    },
+    {
+      "epoch": 0.92442710872745,
+      "grad_norm": 0.3393966555595398,
+      "learning_rate": 8.718013165146275e-06,
+      "loss": 0.1435,
+      "step": 158
+    },
+    {
+      "epoch": 0.9302779132130667,
+      "grad_norm": 0.3675788938999176,
+      "learning_rate": 8.695044586103297e-06,
+      "loss": 0.1488,
+      "step": 159
+    },
+    {
+      "epoch": 0.9361287176986836,
+      "grad_norm": 0.34999918937683105,
+      "learning_rate": 8.671902908935942e-06,
+      "loss": 0.139,
+      "step": 160
+    },
+    {
+      "epoch": 0.9419795221843004,
+      "grad_norm": 0.3778494596481323,
+      "learning_rate": 8.648589217739635e-06,
+      "loss": 0.149,
+      "step": 161
+    },
+    {
+      "epoch": 0.9478303266699171,
+      "grad_norm": 0.34992629289627075,
+      "learning_rate": 8.625104604667965e-06,
+      "loss": 0.1582,
+      "step": 162
+    },
+    {
+      "epoch": 0.9536811311555339,
+      "grad_norm": 0.344200074672699,
+      "learning_rate": 8.601450169881533e-06,
+      "loss": 0.1531,
+      "step": 163
+    },
+    {
+      "epoch": 0.9595319356411507,
+      "grad_norm": 0.3828461170196533,
+      "learning_rate": 8.577627021496413e-06,
+      "loss": 0.1496,
+      "step": 164
+    },
+    {
+      "epoch": 0.9653827401267674,
+      "grad_norm": 0.38192272186279297,
+      "learning_rate": 8.553636275532236e-06,
+      "loss": 0.1595,
+      "step": 165
+    },
+    {
+      "epoch": 0.9712335446123842,
+      "grad_norm": 0.346049964427948,
+      "learning_rate": 8.529479055859918e-06,
+      "loss": 0.1394,
+      "step": 166
+    },
+    {
+      "epoch": 0.977084349098001,
+      "grad_norm": 0.38012537360191345,
+      "learning_rate": 8.505156494148997e-06,
+      "loss": 0.1624,
+      "step": 167
+    },
+    {
+      "epoch": 0.9829351535836177,
+      "grad_norm": 0.3455771505832672,
+      "learning_rate": 8.480669729814635e-06,
+      "loss": 0.1536,
+      "step": 168
+    },
+    {
+      "epoch": 0.9887859580692345,
+      "grad_norm": 0.3532484769821167,
+      "learning_rate": 8.456019909964224e-06,
+      "loss": 0.1457,
+      "step": 169
+    },
+    {
+      "epoch": 0.9946367625548513,
+      "grad_norm": 0.3691612184047699,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.1502,
+      "step": 170
+    },
+    {
+      "epoch": 1.000487567040468,
+      "grad_norm": 0.39640477299690247,
+      "learning_rate": 8.40623573028327e-06,
+      "loss": 0.1672,
+      "step": 171
+    },
+    {
+      "epoch": 1.0063383715260847,
+      "grad_norm": 0.3387565314769745,
+      "learning_rate": 8.381103702643295e-06,
+      "loss": 0.0924,
+      "step": 172
+    },
+    {
+      "epoch": 1.0121891760117017,
+      "grad_norm": 0.3130762577056885,
+      "learning_rate": 8.35581328375915e-06,
+      "loss": 0.0873,
+      "step": 173
+    },
+    {
+      "epoch": 1.0180399804973184,
+      "grad_norm": 0.3515136241912842,
+      "learning_rate": 8.330365658386252e-06,
+      "loss": 0.0971,
+      "step": 174
+    },
+    {
+      "epoch": 1.023890784982935,
+      "grad_norm": 0.32018211483955383,
+      "learning_rate": 8.30476201864451e-06,
+      "loss": 0.0848,
+      "step": 175
+    },
+    {
+      "epoch": 1.029741589468552,
+      "grad_norm": 0.35570186376571655,
+      "learning_rate": 8.27900356396249e-06,
+      "loss": 0.077,
+      "step": 176
+    },
+    {
+      "epoch": 1.0355923939541687,
+      "grad_norm": 0.3432004749774933,
+      "learning_rate": 8.25309150102121e-06,
+      "loss": 0.0922,
+      "step": 177
+    },
+    {
+      "epoch": 1.0414431984397854,
+      "grad_norm": 0.3650023341178894,
+      "learning_rate": 8.227027043697642e-06,
+      "loss": 0.1081,
+      "step": 178
+    },
+    {
+      "epoch": 1.0472940029254023,
+      "grad_norm": 0.3721574544906616,
+      "learning_rate": 8.200811413007808e-06,
+      "loss": 0.0952,
+      "step": 179
+    },
+    {
+      "epoch": 1.053144807411019,
+      "grad_norm": 0.3511905074119568,
+      "learning_rate": 8.174445837049614e-06,
+      "loss": 0.093,
+      "step": 180
+    },
+    {
+      "epoch": 1.0589956118966357,
+      "grad_norm": 0.3371464014053345,
+      "learning_rate": 8.147931550945301e-06,
+      "loss": 0.0873,
+      "step": 181
+    },
+    {
+      "epoch": 1.0648464163822526,
+      "grad_norm": 0.3639083802700043,
+      "learning_rate": 8.121269796783585e-06,
+      "loss": 0.0906,
+      "step": 182
+    },
+    {
+      "epoch": 1.0706972208678693,
+      "grad_norm": 0.3532220125198364,
+      "learning_rate": 8.094461823561473e-06,
+      "loss": 0.0851,
+      "step": 183
+    },
+    {
+      "epoch": 1.076548025353486,
+      "grad_norm": 0.3342878520488739,
+      "learning_rate": 8.06750888712576e-06,
+      "loss": 0.0953,
+      "step": 184
+    },
+    {
+      "epoch": 1.082398829839103,
+      "grad_norm": 0.3148074448108673,
+      "learning_rate": 8.040412250114184e-06,
+      "loss": 0.0837,
+      "step": 185
+    },
+    {
+      "epoch": 1.0882496343247197,
+      "grad_norm": 0.32519224286079407,
+      "learning_rate": 8.013173181896283e-06,
+      "loss": 0.0798,
+      "step": 186
+    },
+    {
+      "epoch": 1.0941004388103364,
+      "grad_norm": 0.3312150239944458,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.0933,
+      "step": 187
+    },
+    {
+      "epoch": 1.0999512432959533,
+      "grad_norm": 0.32089629769325256,
+      "learning_rate": 7.958272862621562e-06,
+      "loss": 0.0922,
+      "step": 188
+    },
+    {
+      "epoch": 1.10580204778157,
+      "grad_norm": 0.35258930921554565,
+      "learning_rate": 7.930614183426074e-06,
+      "loss": 0.0909,
+      "step": 189
+    },
+    {
+      "epoch": 1.1116528522671867,
+      "grad_norm": 0.33893248438835144,
+      "learning_rate": 7.902818216626446e-06,
+      "loss": 0.0929,
+      "step": 190
+    },
+    {
+      "epoch": 1.1175036567528036,
+      "grad_norm": 0.31684961915016174,
+      "learning_rate": 7.874886264353035e-06,
+      "loss": 0.0886,
+      "step": 191
+    },
+    {
+      "epoch": 1.1233544612384203,
+      "grad_norm": 0.3478744328022003,
+      "learning_rate": 7.846819635106569e-06,
+      "loss": 0.0957,
+      "step": 192
+    },
+    {
+      "epoch": 1.129205265724037,
+      "grad_norm": 0.3251475393772125,
+      "learning_rate": 7.818619643696863e-06,
+      "loss": 0.0922,
+      "step": 193
+    },
+    {
+      "epoch": 1.1350560702096537,
+      "grad_norm": 0.29696688055992126,
+      "learning_rate": 7.790287611181217e-06,
+      "loss": 0.0914,
+      "step": 194
+    },
+    {
+      "epoch": 1.1409068746952706,
+      "grad_norm": 0.3044435977935791,
+      "learning_rate": 7.76182486480253e-06,
+      "loss": 0.0892,
+      "step": 195
+    },
+    {
+      "epoch": 1.1467576791808873,
+      "grad_norm": 0.3044622242450714,
+      "learning_rate": 7.733232737927123e-06,
+      "loss": 0.0857,
+      "step": 196
+    },
+    {
+      "epoch": 1.152608483666504,
+      "grad_norm": 0.3341536819934845,
+      "learning_rate": 7.70451256998228e-06,
+      "loss": 0.0906,
+      "step": 197
+    },
+    {
+      "epoch": 1.158459288152121,
+      "grad_norm": 0.2735297679901123,
+      "learning_rate": 7.675665706393502e-06,
+      "loss": 0.0732,
+      "step": 198
+    },
+    {
+      "epoch": 1.1643100926377377,
+      "grad_norm": 0.39707475900650024,
+      "learning_rate": 7.646693498521472e-06,
+      "loss": 0.0917,
+      "step": 199
+    },
+    {
+      "epoch": 1.1701608971233544,
+      "grad_norm": 0.31679078936576843,
+      "learning_rate": 7.617597303598754e-06,
+      "loss": 0.0881,
+      "step": 200
+    },
+    {
+      "epoch": 1.1760117016089713,
+      "grad_norm": 0.360331267118454,
+      "learning_rate": 7.588378484666214e-06,
+      "loss": 0.0954,
+      "step": 201
+    },
+    {
+      "epoch": 1.181862506094588,
+      "grad_norm": 0.38201650977134705,
+      "learning_rate": 7.559038410509161e-06,
+      "loss": 0.0904,
+      "step": 202
+    },
+    {
+      "epoch": 1.1877133105802047,
+      "grad_norm": 0.32335299253463745,
+      "learning_rate": 7.529578455593232e-06,
+      "loss": 0.0945,
+      "step": 203
+    },
+    {
+      "epoch": 1.1935641150658216,
+      "grad_norm": 0.4359491169452667,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.096,
+      "step": 204
+    },
+    {
+      "epoch": 1.1994149195514383,
+      "grad_norm": 0.3149729073047638,
+      "learning_rate": 7.47030442936232e-06,
+      "loss": 0.09,
+      "step": 205
+    },
+    {
+      "epoch": 1.205265724037055,
+      "grad_norm": 0.33973321318626404,
+      "learning_rate": 7.440493134799425e-06,
+      "loss": 0.0913,
+      "step": 206
+    },
+    {
+      "epoch": 1.211116528522672,
+      "grad_norm": 0.30180642008781433,
+      "learning_rate": 7.4105675128517456e-06,
+      "loss": 0.0803,
+      "step": 207
+    },
+    {
+      "epoch": 1.2169673330082886,
+      "grad_norm": 0.345156192779541,
+      "learning_rate": 7.380528965415501e-06,
+      "loss": 0.1082,
+      "step": 208
+    },
+    {
+      "epoch": 1.2228181374939053,
+      "grad_norm": 0.35538923740386963,
+      "learning_rate": 7.35037889967702e-06,
+      "loss": 0.0941,
+      "step": 209
+    },
+    {
+      "epoch": 1.2286689419795223,
+      "grad_norm": 0.3383888006210327,
+      "learning_rate": 7.320118728046818e-06,
+      "loss": 0.0977,
+      "step": 210
+    },
+    {
+      "epoch": 1.234519746465139,
+      "grad_norm": 0.32048848271369934,
+      "learning_rate": 7.289749868093432e-06,
+      "loss": 0.0997,
+      "step": 211
+    },
+    {
+      "epoch": 1.2403705509507557,
+      "grad_norm": 0.30647850036621094,
+      "learning_rate": 7.259273742477017e-06,
+      "loss": 0.0735,
+      "step": 212
+    },
+    {
+      "epoch": 1.2462213554363726,
+      "grad_norm": 0.3137127757072449,
+      "learning_rate": 7.2286917788826926e-06,
+      "loss": 0.086,
+      "step": 213
+    },
+    {
+      "epoch": 1.2520721599219893,
+      "grad_norm": 0.3300592005252838,
+      "learning_rate": 7.19800540995367e-06,
+      "loss": 0.1001,
+      "step": 214
+    },
+    {
+      "epoch": 1.257922964407606,
+      "grad_norm": 0.36561137437820435,
+      "learning_rate": 7.167216073224136e-06,
+      "loss": 0.0939,
+      "step": 215
+    },
+    {
+      "epoch": 1.263773768893223,
+      "grad_norm": 0.32352930307388306,
+      "learning_rate": 7.136325211051905e-06,
+      "loss": 0.0842,
+      "step": 216
+    },
+    {
+      "epoch": 1.2696245733788396,
+      "grad_norm": 0.3289717733860016,
+      "learning_rate": 7.1053342705508564e-06,
+      "loss": 0.0935,
+      "step": 217
+    },
+    {
+      "epoch": 1.2754753778644563,
+      "grad_norm": 0.28205370903015137,
+      "learning_rate": 7.074244703523137e-06,
+      "loss": 0.0778,
+      "step": 218
+    },
+    {
+      "epoch": 1.2813261823500732,
+      "grad_norm": 0.38977792859077454,
+      "learning_rate": 7.043057966391158e-06,
+      "loss": 0.0956,
+      "step": 219
+    },
+    {
+      "epoch": 1.28717698683569,
+      "grad_norm": 0.3073525130748749,
+      "learning_rate": 7.011775520129363e-06,
+      "loss": 0.0863,
+      "step": 220
+    },
+    {
+      "epoch": 1.2930277913213066,
+      "grad_norm": 0.3111942410469055,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.0834,
+      "step": 221
+    },
+    {
+      "epoch": 1.2988785958069236,
+      "grad_norm": 0.3141816556453705,
+      "learning_rate": 6.948929366463397e-06,
+      "loss": 0.0843,
+      "step": 222
+    },
+    {
+      "epoch": 1.3047294002925403,
+      "grad_norm": 0.3614446222782135,
+      "learning_rate": 6.9173686031512595e-06,
+      "loss": 0.1021,
+      "step": 223
+    },
+    {
+      "epoch": 1.310580204778157,
+      "grad_norm": 0.3350818157196045,
+      "learning_rate": 6.885718018755448e-06,
+      "loss": 0.0871,
+      "step": 224
+    },
+    {
+      "epoch": 1.3164310092637739,
+      "grad_norm": 0.32823216915130615,
+      "learning_rate": 6.8539790959798045e-06,
+      "loss": 0.0916,
+      "step": 225
+    },
+    {
+      "epoch": 1.3222818137493906,
+      "grad_norm": 0.382249116897583,
+      "learning_rate": 6.822153321666469e-06,
+      "loss": 0.0904,
+      "step": 226
+    },
+    {
+      "epoch": 1.3281326182350073,
+      "grad_norm": 0.32061290740966797,
+      "learning_rate": 6.790242186726231e-06,
+      "loss": 0.0966,
+      "step": 227
+    },
+    {
+      "epoch": 1.3339834227206242,
+      "grad_norm": 0.32373279333114624,
+      "learning_rate": 6.758247186068684e-06,
+      "loss": 0.0891,
+      "step": 228
+    },
+    {
+      "epoch": 1.339834227206241,
+      "grad_norm": 0.32146140933036804,
+      "learning_rate": 6.7261698185322e-06,
+      "loss": 0.09,
+      "step": 229
+    },
+    {
+      "epoch": 1.3456850316918576,
+      "grad_norm": 0.33953243494033813,
+      "learning_rate": 6.6940115868137065e-06,
+      "loss": 0.0877,
+      "step": 230
+    },
+    {
+      "epoch": 1.3515358361774745,
+      "grad_norm": 0.3054323196411133,
+      "learning_rate": 6.6617739973982985e-06,
+      "loss": 0.088,
+      "step": 231
+    },
+    {
+      "epoch": 1.3573866406630912,
+      "grad_norm": 0.34463798999786377,
+      "learning_rate": 6.629458560488664e-06,
+      "loss": 0.1081,
+      "step": 232
+    },
+    {
+      "epoch": 1.363237445148708,
+      "grad_norm": 0.3094691336154938,
+      "learning_rate": 6.597066789934336e-06,
+      "loss": 0.089,
+      "step": 233
+    },
+    {
+      "epoch": 1.3690882496343248,
+      "grad_norm": 0.3243754506111145,
+      "learning_rate": 6.5646002031607726e-06,
+      "loss": 0.1017,
+      "step": 234
+    },
+    {
+      "epoch": 1.3749390541199416,
+      "grad_norm": 0.3523649573326111,
+      "learning_rate": 6.5320603210982745e-06,
+      "loss": 0.0976,
+      "step": 235
+    },
+    {
+      "epoch": 1.3807898586055583,
+      "grad_norm": 0.32277393341064453,
+      "learning_rate": 6.499448668110735e-06,
+      "loss": 0.0987,
+      "step": 236
+    },
+    {
+      "epoch": 1.3866406630911752,
+      "grad_norm": 0.36676648259162903,
+      "learning_rate": 6.466766771924231e-06,
+      "loss": 0.0962,
+      "step": 237
+    },
+    {
+      "epoch": 1.3924914675767919,
+      "grad_norm": 0.3382190465927124,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.0997,
+      "step": 238
+    },
+    {
+      "epoch": 1.3983422720624086,
+      "grad_norm": 0.3056662082672119,
+      "learning_rate": 6.401198377239979e-06,
+      "loss": 0.0832,
+      "step": 239
+    },
+    {
+      "epoch": 1.4041930765480253,
+      "grad_norm": 0.34704071283340454,
+      "learning_rate": 6.368314950360416e-06,
+      "loss": 0.0989,
+      "step": 240
+    },
+    {
+      "epoch": 1.4100438810336422,
+      "grad_norm": 0.3333982527256012,
+      "learning_rate": 6.3353674233743585e-06,
+      "loss": 0.1005,
+      "step": 241
+    },
+    {
+      "epoch": 1.415894685519259,
+      "grad_norm": 0.3286687135696411,
+      "learning_rate": 6.302357339742245e-06,
+      "loss": 0.089,
+      "step": 242
+    },
+    {
+      "epoch": 1.4217454900048756,
+      "grad_norm": 0.33592113852500916,
+      "learning_rate": 6.269286245855039e-06,
+      "loss": 0.0927,
+      "step": 243
+    },
+    {
+      "epoch": 1.4275962944904925,
+      "grad_norm": 0.3280174434185028,
+      "learning_rate": 6.236155690961795e-06,
+      "loss": 0.085,
+      "step": 244
+    },
+    {
+      "epoch": 1.4334470989761092,
+      "grad_norm": 0.31295254826545715,
+      "learning_rate": 6.202967227097073e-06,
+      "loss": 0.0944,
+      "step": 245
+    },
+    {
+      "epoch": 1.439297903461726,
+      "grad_norm": 0.3453296422958374,
+      "learning_rate": 6.169722409008244e-06,
+      "loss": 0.0878,
+      "step": 246
+    },
+    {
+      "epoch": 1.4451487079473426,
+      "grad_norm": 0.3456035852432251,
+      "learning_rate": 6.136422794082645e-06,
+      "loss": 0.0943,
+      "step": 247
+    },
+    {
+      "epoch": 1.4509995124329595,
+      "grad_norm": 0.31323128938674927,
+      "learning_rate": 6.10306994227463e-06,
+      "loss": 0.0759,
+      "step": 248
+    },
+    {
+      "epoch": 1.4568503169185762,
+      "grad_norm": 0.33041155338287354,
+      "learning_rate": 6.0696654160324875e-06,
+      "loss": 0.098,
+      "step": 249
+    },
+    {
+      "epoch": 1.462701121404193,
+      "grad_norm": 0.3976047933101654,
+      "learning_rate": 6.0362107802252486e-06,
+      "loss": 0.1005,
+      "step": 250
+    },
+    {
+      "epoch": 1.4685519258898099,
+      "grad_norm": 0.3161430358886719,
+      "learning_rate": 6.002707602069377e-06,
+      "loss": 0.0909,
+      "step": 251
+    },
+    {
+      "epoch": 1.4744027303754266,
+      "grad_norm": 0.36212068796157837,
+      "learning_rate": 5.9691574510553505e-06,
+      "loss": 0.1077,
+      "step": 252
+    },
+    {
+      "epoch": 1.4802535348610433,
+      "grad_norm": 0.3128092586994171,
+      "learning_rate": 5.935561898874142e-06,
+      "loss": 0.0965,
+      "step": 253
+    },
+    {
+      "epoch": 1.4861043393466602,
+      "grad_norm": 0.29555660486221313,
+      "learning_rate": 5.901922519343586e-06,
+      "loss": 0.0938,
+      "step": 254
+    },
+    {
+      "epoch": 1.491955143832277,
+      "grad_norm": 0.3516538143157959,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.0948,
+      "step": 255
+    },
+    {
+      "epoch": 1.4978059483178936,
+      "grad_norm": 0.33568522334098816,
+      "learning_rate": 5.834518583697628e-06,
+      "loss": 0.1097,
+      "step": 256
+    },
+    {
+      "epoch": 1.5036567528035105,
+      "grad_norm": 0.3301846385002136,
+      "learning_rate": 5.800757185188195e-06,
+      "loss": 0.096,
+      "step": 257
+    },
+    {
+      "epoch": 1.5095075572891272,
+      "grad_norm": 0.36975666880607605,
+      "learning_rate": 5.766958274393428e-06,
+      "loss": 0.1021,
+      "step": 258
+    },
+    {
+      "epoch": 1.515358361774744,
+      "grad_norm": 0.36187541484832764,
+      "learning_rate": 5.733123434657704e-06,
+      "loss": 0.0978,
+      "step": 259
+    },
+    {
+      "epoch": 1.5212091662603608,
+      "grad_norm": 0.302735298871994,
+      "learning_rate": 5.699254251008524e-06,
+      "loss": 0.0863,
+      "step": 260
+    },
+    {
+      "epoch": 1.5270599707459775,
+      "grad_norm": 0.3669283986091614,
+      "learning_rate": 5.66535231008227e-06,
+      "loss": 0.0993,
+      "step": 261
+    },
+    {
+      "epoch": 1.5329107752315942,
+      "grad_norm": 0.30971550941467285,
+      "learning_rate": 5.631419200049867e-06,
+      "loss": 0.094,
+      "step": 262
+    },
+    {
+      "epoch": 1.5387615797172112,
+      "grad_norm": 0.31271669268608093,
+      "learning_rate": 5.597456510542395e-06,
+      "loss": 0.0784,
+      "step": 263
+    },
+    {
+      "epoch": 1.5446123842028279,
+      "grad_norm": 0.3437775671482086,
+      "learning_rate": 5.5634658325766066e-06,
+      "loss": 0.094,
+      "step": 264
+    },
+    {
+      "epoch": 1.5504631886884446,
+      "grad_norm": 0.30059608817100525,
+      "learning_rate": 5.529448758480408e-06,
+      "loss": 0.0837,
+      "step": 265
+    },
+    {
+      "epoch": 1.5563139931740615,
+      "grad_norm": 0.3427652418613434,
+      "learning_rate": 5.495406881818256e-06,
+      "loss": 0.0974,
+      "step": 266
+    },
+    {
+      "epoch": 1.5621647976596782,
+      "grad_norm": 0.325862318277359,
+      "learning_rate": 5.46134179731651e-06,
+      "loss": 0.0941,
+      "step": 267
+    },
+    {
+      "epoch": 1.568015602145295,
+      "grad_norm": 0.2897391617298126,
+      "learning_rate": 5.427255100788726e-06,
+      "loss": 0.0892,
+      "step": 268
+    },
+    {
+      "epoch": 1.5738664066309118,
+      "grad_norm": 0.33088555932044983,
+      "learning_rate": 5.393148389060893e-06,
+      "loss": 0.09,
+      "step": 269
+    },
+    {
+      "epoch": 1.5797172111165285,
+      "grad_norm": 0.3650970757007599,
+      "learning_rate": 5.359023259896638e-06,
+      "loss": 0.0931,
+      "step": 270
+    },
+    {
+      "epoch": 1.5855680156021452,
+      "grad_norm": 0.34107041358947754,
+      "learning_rate": 5.3248813119223665e-06,
+      "loss": 0.0937,
+      "step": 271
+    },
+    {
+      "epoch": 1.5914188200877621,
+      "grad_norm": 0.3320484459400177,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.1058,
+      "step": 272
+    },
+    {
+      "epoch": 1.5972696245733788,
+      "grad_norm": 0.31170666217803955,
+      "learning_rate": 5.2565533579139484e-06,
+      "loss": 0.0923,
+      "step": 273
+    },
+    {
+      "epoch": 1.6031204290589955,
+      "grad_norm": 0.3246054947376251,
+      "learning_rate": 5.222370552772353e-06,
+      "loss": 0.0999,
+      "step": 274
+    },
+    {
+      "epoch": 1.6089712335446125,
+      "grad_norm": 0.35101330280303955,
+      "learning_rate": 5.188177330455886e-06,
+      "loss": 0.1082,
+      "step": 275
+    },
+    {
+      "epoch": 1.6148220380302292,
+      "grad_norm": 0.29805803298950195,
+      "learning_rate": 5.153975292780852e-06,
+      "loss": 0.0867,
+      "step": 276
+    },
+    {
+      "epoch": 1.6206728425158459,
+      "grad_norm": 0.32440170645713806,
+      "learning_rate": 5.119766041976516e-06,
+      "loss": 0.0936,
+      "step": 277
+    },
+    {
+      "epoch": 1.6265236470014628,
+      "grad_norm": 0.33313047885894775,
+      "learning_rate": 5.085551180610046e-06,
+      "loss": 0.0929,
+      "step": 278
+    },
+    {
+      "epoch": 1.6323744514870795,
+      "grad_norm": 0.3095255494117737,
+      "learning_rate": 5.05133231151145e-06,
+      "loss": 0.0847,
+      "step": 279
+    },
+    {
+      "epoch": 1.6382252559726962,
+      "grad_norm": 0.3372449278831482,
+      "learning_rate": 5.017111037698477e-06,
+      "loss": 0.104,
+      "step": 280
+    },
+    {
+      "epoch": 1.6494392979034618,
+      "grad_norm": 0.32717257738113403,
+      "learning_rate": 4.9828889623015265e-06,
+      "loss": 0.0863,
+      "step": 281
+    },
+    {
+      "epoch": 1.6552901023890785,
+      "grad_norm": 0.3508462607860565,
+      "learning_rate": 4.948667688488552e-06,
+      "loss": 0.0937,
+      "step": 282
+    },
+    {
+      "epoch": 1.6611409068746954,
+      "grad_norm": 0.3077023923397064,
+      "learning_rate": 4.9144488193899546e-06,
+      "loss": 0.0933,
+      "step": 283
+    },
+    {
+      "epoch": 1.6669917113603119,
+      "grad_norm": 0.3831559419631958,
+      "learning_rate": 4.880233958023486e-06,
+      "loss": 0.1023,
+      "step": 284
+    },
+    {
+      "epoch": 1.6728425158459288,
+      "grad_norm": 0.31356075406074524,
+      "learning_rate": 4.846024707219149e-06,
+      "loss": 0.088,
+      "step": 285
+    },
+    {
+      "epoch": 1.6786933203315457,
+      "grad_norm": 0.35236048698425293,
+      "learning_rate": 4.811822669544115e-06,
+      "loss": 0.0942,
+      "step": 286
+    },
+    {
+      "epoch": 1.6845441248171622,
+      "grad_norm": 0.32862260937690735,
+      "learning_rate": 4.777629447227649e-06,
+      "loss": 0.1004,
+      "step": 287
+    },
+    {
+      "epoch": 1.6903949293027791,
+      "grad_norm": 0.29887956380844116,
+      "learning_rate": 4.7434466420860515e-06,
+      "loss": 0.0838,
+      "step": 288
+    },
+    {
+      "epoch": 1.696245733788396,
+      "grad_norm": 0.38082054257392883,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.0955,
+      "step": 289
+    },
+    {
+      "epoch": 1.7020965382740125,
+      "grad_norm": 0.3033042848110199,
+      "learning_rate": 4.675118688077634e-06,
+      "loss": 0.0907,
+      "step": 290
+    },
+    {
+      "epoch": 1.7079473427596294,
+      "grad_norm": 0.3312883973121643,
+      "learning_rate": 4.640976740103363e-06,
+      "loss": 0.0922,
+      "step": 291
+    },
+    {
+      "epoch": 1.7137981472452464,
+      "grad_norm": 0.3242630064487457,
+      "learning_rate": 4.606851610939108e-06,
+      "loss": 0.0918,
+      "step": 292
+    },
+    {
+      "epoch": 1.7196489517308629,
+      "grad_norm": 0.3354322612285614,
+      "learning_rate": 4.572744899211275e-06,
+      "loss": 0.0988,
+      "step": 293
+    },
+    {
+      "epoch": 1.7254997562164798,
+      "grad_norm": 0.3046918213367462,
+      "learning_rate": 4.53865820268349e-06,
+      "loss": 0.0829,
+      "step": 294
+    },
+    {
+      "epoch": 1.7313505607020967,
+      "grad_norm": 0.3330130875110626,
+      "learning_rate": 4.504593118181745e-06,
+      "loss": 0.1022,
+      "step": 295
+    },
+    {
+      "epoch": 1.7372013651877132,
+      "grad_norm": 0.31168803572654724,
+      "learning_rate": 4.470551241519594e-06,
+      "loss": 0.0841,
+      "step": 296
+    },
+    {
+      "epoch": 1.74305216967333,
+      "grad_norm": 0.3428613841533661,
+      "learning_rate": 4.436534167423395e-06,
+      "loss": 0.0921,
+      "step": 297
+    },
+    {
+      "epoch": 1.748902974158947,
+      "grad_norm": 0.33911219239234924,
+      "learning_rate": 4.402543489457607e-06,
+      "loss": 0.0969,
+      "step": 298
+    },
+    {
+      "epoch": 1.7547537786445635,
+      "grad_norm": 0.3178160488605499,
+      "learning_rate": 4.368580799950133e-06,
+      "loss": 0.0884,
+      "step": 299
+    },
+    {
+      "epoch": 1.7606045831301804,
+      "grad_norm": 0.3277307152748108,
+      "learning_rate": 4.334647689917734e-06,
+      "loss": 0.0974,
+      "step": 300
+    },
+    {
+      "epoch": 1.7664553876157971,
+      "grad_norm": 0.3535825312137604,
+      "learning_rate": 4.300745748991478e-06,
+      "loss": 0.0896,
+      "step": 301
+    },
+    {
+      "epoch": 1.7723061921014138,
+      "grad_norm": 0.32610517740249634,
+      "learning_rate": 4.266876565342298e-06,
+      "loss": 0.0994,
+      "step": 302
+    },
+    {
+      "epoch": 1.7781569965870307,
+      "grad_norm": 0.3436540961265564,
+      "learning_rate": 4.233041725606573e-06,
+      "loss": 0.0968,
+      "step": 303
+    },
+    {
+      "epoch": 1.7840078010726474,
+      "grad_norm": 0.35339972376823425,
+      "learning_rate": 4.199242814811807e-06,
+      "loss": 0.0964,
+      "step": 304
+    },
+    {
+      "epoch": 1.7898586055582641,
+      "grad_norm": 0.3242701292037964,
+      "learning_rate": 4.1654814163023735e-06,
+      "loss": 0.0817,
+      "step": 305
+    },
+    {
+      "epoch": 1.795709410043881,
+      "grad_norm": 0.38222551345825195,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.099,
+      "step": 306
+    },
+    {
+      "epoch": 1.8015602145294978,
+      "grad_norm": 0.32425937056541443,
+      "learning_rate": 4.098077480656415e-06,
+      "loss": 0.0873,
+      "step": 307
+    },
+    {
+      "epoch": 1.8074110190151145,
+      "grad_norm": 0.36380070447921753,
+      "learning_rate": 4.064438101125859e-06,
+      "loss": 0.0973,
+      "step": 308
+    },
+    {
+      "epoch": 1.8132618235007314,
+      "grad_norm": 0.34305286407470703,
+      "learning_rate": 4.03084254894465e-06,
+      "loss": 0.0922,
+      "step": 309
+    },
+    {
+      "epoch": 1.819112627986348,
+      "grad_norm": 0.353582501411438,
+      "learning_rate": 3.997292397930624e-06,
+      "loss": 0.0872,
+      "step": 310
+    },
+    {
+      "epoch": 1.8249634324719648,
+      "grad_norm": 0.29907920956611633,
+      "learning_rate": 3.963789219774753e-06,
+      "loss": 0.0845,
+      "step": 311
+    },
+    {
+      "epoch": 1.8308142369575817,
+      "grad_norm": 0.3310573399066925,
+      "learning_rate": 3.930334583967514e-06,
+      "loss": 0.0941,
+      "step": 312
+    },
+    {
+      "epoch": 1.8366650414431984,
+      "grad_norm": 0.3727741241455078,
+      "learning_rate": 3.896930057725372e-06,
+      "loss": 0.0807,
+      "step": 313
+    },
+    {
+      "epoch": 1.8425158459288151,
+      "grad_norm": 0.3489404022693634,
+      "learning_rate": 3.863577205917356e-06,
+      "loss": 0.1051,
+      "step": 314
+    },
+    {
+      "epoch": 1.848366650414432,
+      "grad_norm": 0.3304194509983063,
+      "learning_rate": 3.8302775909917585e-06,
+      "loss": 0.0937,
+      "step": 315
+    },
+    {
+      "epoch": 1.8542174549000487,
+      "grad_norm": 0.31810325384140015,
+      "learning_rate": 3.7970327729029288e-06,
+      "loss": 0.0917,
+      "step": 316
+    },
+    {
+      "epoch": 1.8600682593856654,
+      "grad_norm": 0.3284529149532318,
+      "learning_rate": 3.7638443090382067e-06,
+      "loss": 0.0864,
+      "step": 317
+    },
+    {
+      "epoch": 1.8659190638712824,
+      "grad_norm": 0.34479424357414246,
+      "learning_rate": 3.730713754144961e-06,
+      "loss": 0.0938,
+      "step": 318
+    },
+    {
+      "epoch": 1.871769868356899,
+      "grad_norm": 0.32104262709617615,
+      "learning_rate": 3.6976426602577565e-06,
+      "loss": 0.0866,
+      "step": 319
+    },
+    {
+      "epoch": 1.8776206728425158,
+      "grad_norm": 0.32675501704216003,
+      "learning_rate": 3.6646325766256423e-06,
+      "loss": 0.0841,
+      "step": 320
+    },
+    {
+      "epoch": 1.8834714773281327,
+      "grad_norm": 0.3269306421279907,
+      "learning_rate": 3.6316850496395863e-06,
+      "loss": 0.0926,
+      "step": 321
+    },
+    {
+      "epoch": 1.8893222818137494,
+      "grad_norm": 0.32884150743484497,
+      "learning_rate": 3.598801622760021e-06,
+      "loss": 0.0816,
+      "step": 322
+    },
+    {
+      "epoch": 1.895173086299366,
+      "grad_norm": 0.3181195557117462,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.0887,
+      "step": 323
+    },
+    {
+      "epoch": 1.901023890784983,
+      "grad_norm": 0.3327188789844513,
+      "learning_rate": 3.5332332280757706e-06,
+      "loss": 0.0966,
+      "step": 324
+    },
+    {
+      "epoch": 1.9068746952705997,
+      "grad_norm": 0.3728068470954895,
+      "learning_rate": 3.5005513318892666e-06,
+      "loss": 0.0991,
+      "step": 325
+    },
+    {
+      "epoch": 1.9127254997562164,
+      "grad_norm": 0.37355464696884155,
+      "learning_rate": 3.4679396789017263e-06,
+      "loss": 0.0867,
+      "step": 326
+    },
+    {
+      "epoch": 1.9185763042418333,
+      "grad_norm": 0.32492557168006897,
+      "learning_rate": 3.4353997968392295e-06,
+      "loss": 0.0894,
+      "step": 327
+    },
+    {
+      "epoch": 1.92442710872745,
+      "grad_norm": 0.322022944688797,
+      "learning_rate": 3.402933210065665e-06,
+      "loss": 0.0894,
+      "step": 328
+    },
+    {
+      "epoch": 1.9302779132130667,
+      "grad_norm": 0.31964507699012756,
+      "learning_rate": 3.3705414395113354e-06,
+      "loss": 0.0918,
+      "step": 329
+    },
+    {
+      "epoch": 1.9361287176986837,
+      "grad_norm": 0.33390405774116516,
+      "learning_rate": 3.3382260026017027e-06,
+      "loss": 0.0884,
+      "step": 330
+    },
+    {
+      "epoch": 1.9419795221843004,
+      "grad_norm": 0.33786076307296753,
+      "learning_rate": 3.305988413186295e-06,
+      "loss": 0.0872,
+      "step": 331
+    },
+    {
+      "epoch": 1.947830326669917,
+      "grad_norm": 0.3263327181339264,
+      "learning_rate": 3.2738301814678015e-06,
+      "loss": 0.0922,
+      "step": 332
+    },
+    {
+      "epoch": 1.953681131155534,
+      "grad_norm": 0.3341035544872284,
+      "learning_rate": 3.241752813931316e-06,
+      "loss": 0.0855,
+      "step": 333
+    },
+    {
+      "epoch": 1.9595319356411507,
+      "grad_norm": 0.38113948702812195,
+      "learning_rate": 3.2097578132737716e-06,
+      "loss": 0.1033,
+      "step": 334
+    },
+    {
+      "epoch": 1.9653827401267674,
+      "grad_norm": 0.33053913712501526,
+      "learning_rate": 3.1778466783335328e-06,
+      "loss": 0.0958,
+      "step": 335
+    },
+    {
+      "epoch": 1.9712335446123843,
+      "grad_norm": 0.34964510798454285,
+      "learning_rate": 3.1460209040201967e-06,
+      "loss": 0.0886,
+      "step": 336
+    },
+    {
+      "epoch": 1.977084349098001,
+      "grad_norm": 0.3344588279724121,
+      "learning_rate": 3.114281981244553e-06,
+      "loss": 0.0925,
+      "step": 337
+    },
+    {
+      "epoch": 1.9829351535836177,
+      "grad_norm": 0.32202234864234924,
+      "learning_rate": 3.082631396848743e-06,
+      "loss": 0.0954,
+      "step": 338
+    },
+    {
+      "epoch": 1.9887859580692346,
+      "grad_norm": 0.3456474542617798,
+      "learning_rate": 3.0510706335366034e-06,
+      "loss": 0.0856,
+      "step": 339
+    },
+    {
+      "epoch": 1.9946367625548513,
+      "grad_norm": 0.3227405250072479,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.0878,
+      "step": 340
+    },
+    {
+      "epoch": 2.000487567040468,
+      "grad_norm": 0.31147223711013794,
+      "learning_rate": 2.9882244798706372e-06,
+      "loss": 0.0759,
+      "step": 341
+    },
+    {
+      "epoch": 2.006338371526085,
+      "grad_norm": 0.2763703763484955,
+      "learning_rate": 2.956942033608843e-06,
+      "loss": 0.0525,
+      "step": 342
+    },
+    {
+      "epoch": 2.0121891760117014,
+      "grad_norm": 0.29425641894340515,
+      "learning_rate": 2.9257552964768644e-06,
+      "loss": 0.0601,
+      "step": 343
+    },
+    {
+      "epoch": 2.0180399804973184,
+      "grad_norm": 0.2795559763908386,
+      "learning_rate": 2.8946657294491452e-06,
+      "loss": 0.0573,
+      "step": 344
+    },
+    {
+      "epoch": 2.0238907849829353,
+      "grad_norm": 0.34892964363098145,
+      "learning_rate": 2.863674788948097e-06,
+      "loss": 0.0628,
+      "step": 345
+    },
+    {
+      "epoch": 2.0297415894685518,
+      "grad_norm": 0.28666457533836365,
+      "learning_rate": 2.832783926775865e-06,
+      "loss": 0.0524,
+      "step": 346
+    },
+    {
+      "epoch": 2.0355923939541687,
+      "grad_norm": 0.26126629114151,
+      "learning_rate": 2.8019945900463307e-06,
+      "loss": 0.0578,
+      "step": 347
+    },
+    {
+      "epoch": 2.0414431984397856,
+      "grad_norm": 0.2673165500164032,
+      "learning_rate": 2.771308221117309e-06,
+      "loss": 0.0574,
+      "step": 348
+    },
+    {
+      "epoch": 2.047294002925402,
+      "grad_norm": 0.2941865921020508,
+      "learning_rate": 2.740726257522987e-06,
+      "loss": 0.0551,
+      "step": 349
+    },
+    {
+      "epoch": 2.053144807411019,
+      "grad_norm": 0.2612977623939514,
+      "learning_rate": 2.7102501319065706e-06,
+      "loss": 0.0644,
+      "step": 350
+    },
+    {
+      "epoch": 2.058995611896636,
+      "grad_norm": 0.2891154885292053,
+      "learning_rate": 2.6798812719531843e-06,
+      "loss": 0.0563,
+      "step": 351
+    },
+    {
+      "epoch": 2.0648464163822524,
+      "grad_norm": 0.2692639231681824,
+      "learning_rate": 2.6496211003229795e-06,
+      "loss": 0.0541,
+      "step": 352
+    },
+    {
+      "epoch": 2.0706972208678693,
+      "grad_norm": 0.3014177680015564,
+      "learning_rate": 2.6194710345845e-06,
+      "loss": 0.0502,
+      "step": 353
+    },
+    {
+      "epoch": 2.0765480253534863,
+      "grad_norm": 0.28264397382736206,
+      "learning_rate": 2.5894324871482557e-06,
+      "loss": 0.0566,
+      "step": 354
+    },
+    {
+      "epoch": 2.0823988298391027,
+      "grad_norm": 0.2884339392185211,
+      "learning_rate": 2.559506865200576e-06,
+      "loss": 0.0527,
+      "step": 355
+    },
+    {
+      "epoch": 2.0882496343247197,
+      "grad_norm": 0.26103538274765015,
+      "learning_rate": 2.529695570637679e-06,
+      "loss": 0.0596,
+      "step": 356
+    },
+    {
+      "epoch": 2.0941004388103366,
+      "grad_norm": 0.2645220160484314,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.0564,
+      "step": 357
+    },
+    {
+      "epoch": 2.099951243295953,
+      "grad_norm": 0.3041948080062866,
+      "learning_rate": 2.4704215444067684e-06,
+      "loss": 0.0529,
+      "step": 358
+    },
+    {
+      "epoch": 2.10580204778157,
+      "grad_norm": 0.26852619647979736,
+      "learning_rate": 2.4409615894908407e-06,
+      "loss": 0.0551,
+      "step": 359
+    },
+    {
+      "epoch": 2.111652852267187,
+      "grad_norm": 0.2973073422908783,
+      "learning_rate": 2.411621515333788e-06,
+      "loss": 0.0616,
+      "step": 360
+    },
+    {
+      "epoch": 2.1175036567528034,
+      "grad_norm": 0.2823100686073303,
+      "learning_rate": 2.3824026964012487e-06,
+      "loss": 0.0616,
+      "step": 361
+    },
+    {
+      "epoch": 2.1233544612384203,
+      "grad_norm": 0.25822895765304565,
+      "learning_rate": 2.35330650147853e-06,
+      "loss": 0.0512,
+      "step": 362
+    },
+    {
+      "epoch": 2.1292052657240372,
+      "grad_norm": 0.34585779905319214,
+      "learning_rate": 2.324334293606499e-06,
+      "loss": 0.0495,
+      "step": 363
+    },
+    {
+      "epoch": 2.1350560702096537,
+      "grad_norm": 0.2767939567565918,
+      "learning_rate": 2.2954874300177197e-06,
+      "loss": 0.0561,
+      "step": 364
+    },
+    {
+      "epoch": 2.1409068746952706,
+      "grad_norm": 0.27340444922447205,
+      "learning_rate": 2.266767262072878e-06,
+      "loss": 0.0562,
+      "step": 365
+    },
+    {
+      "epoch": 2.1467576791808876,
+      "grad_norm": 0.273384690284729,
+      "learning_rate": 2.238175135197471e-06,
+      "loss": 0.0593,
+      "step": 366
+    },
+    {
+      "epoch": 2.152608483666504,
+      "grad_norm": 0.28088316321372986,
+      "learning_rate": 2.2097123888187825e-06,
+      "loss": 0.0505,
+      "step": 367
+    },
+    {
+      "epoch": 2.158459288152121,
+      "grad_norm": 0.2613745331764221,
+      "learning_rate": 2.181380356303139e-06,
+      "loss": 0.0525,
+      "step": 368
+    },
+    {
+      "epoch": 2.164310092637738,
+      "grad_norm": 0.2488614320755005,
+      "learning_rate": 2.1531803648934333e-06,
+      "loss": 0.0498,
+      "step": 369
+    },
+    {
+      "epoch": 2.1701608971233544,
+      "grad_norm": 0.2990882098674774,
+      "learning_rate": 2.1251137356469677e-06,
+      "loss": 0.0551,
+      "step": 370
+    },
+    {
+      "epoch": 2.1760117016089713,
+      "grad_norm": 0.30025023221969604,
+      "learning_rate": 2.0971817833735548e-06,
+      "loss": 0.055,
+      "step": 371
+    },
+    {
+      "epoch": 2.181862506094588,
+      "grad_norm": 0.2645871639251709,
+      "learning_rate": 2.069385816573928e-06,
+      "loss": 0.0564,
+      "step": 372
+    },
+    {
+      "epoch": 2.1877133105802047,
+      "grad_norm": 0.29934531450271606,
+      "learning_rate": 2.0417271373784403e-06,
+      "loss": 0.0613,
+      "step": 373
+    },
+    {
+      "epoch": 2.1935641150658216,
+      "grad_norm": 0.2638642489910126,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.0539,
+      "step": 374
+    },
+    {
+      "epoch": 2.1994149195514385,
+      "grad_norm": 0.2566313147544861,
+      "learning_rate": 1.9868268181037186e-06,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 2.205265724037055,
+      "grad_norm": 0.274949312210083,
+      "learning_rate": 1.9595877498858175e-06,
+      "loss": 0.0644,
+      "step": 376
+    },
+    {
+      "epoch": 2.211116528522672,
+      "grad_norm": 0.21347293257713318,
+      "learning_rate": 1.9324911128742406e-06,
+      "loss": 0.046,
+      "step": 377
+    },
+    {
+      "epoch": 2.216967333008289,
+      "grad_norm": 0.296029657125473,
+      "learning_rate": 1.9055381764385272e-06,
+      "loss": 0.0674,
+      "step": 378
+    },
+    {
+      "epoch": 2.2228181374939053,
+      "grad_norm": 0.3009437024593353,
+      "learning_rate": 1.8787302032164168e-06,
+      "loss": 0.0635,
+      "step": 379
+    },
+    {
+      "epoch": 2.2286689419795223,
+      "grad_norm": 0.2573295831680298,
+      "learning_rate": 1.8520684490547014e-06,
+      "loss": 0.0621,
+      "step": 380
+    },
+    {
+      "epoch": 2.234519746465139,
+      "grad_norm": 0.28992000222206116,
+      "learning_rate": 1.8255541629503865e-06,
+      "loss": 0.051,
+      "step": 381
+    },
+    {
+      "epoch": 2.2403705509507557,
+      "grad_norm": 0.2807430028915405,
+      "learning_rate": 1.7991885869921928e-06,
+      "loss": 0.056,
+      "step": 382
+    },
+    {
+      "epoch": 2.2462213554363726,
+      "grad_norm": 0.2580874562263489,
+      "learning_rate": 1.7729729563023613e-06,
+      "loss": 0.0576,
+      "step": 383
+    },
+    {
+      "epoch": 2.2520721599219895,
+      "grad_norm": 0.27799367904663086,
+      "learning_rate": 1.746908498978791e-06,
+      "loss": 0.0491,
+      "step": 384
+    },
+    {
+      "epoch": 2.257922964407606,
+      "grad_norm": 0.28631195425987244,
+      "learning_rate": 1.7209964360375137e-06,
+      "loss": 0.0516,
+      "step": 385
+    },
+    {
+      "epoch": 2.263773768893223,
+      "grad_norm": 0.2720945477485657,
+      "learning_rate": 1.6952379813554914e-06,
+      "loss": 0.0525,
+      "step": 386
+    },
+    {
+      "epoch": 2.26962457337884,
+      "grad_norm": 0.2580566108226776,
+      "learning_rate": 1.6696343416137495e-06,
+      "loss": 0.0599,
+      "step": 387
+    },
+    {
+      "epoch": 2.2754753778644563,
+      "grad_norm": 0.2627420723438263,
+      "learning_rate": 1.6441867162408514e-06,
+      "loss": 0.0531,
+      "step": 388
+    },
+    {
+      "epoch": 2.2813261823500732,
+      "grad_norm": 0.2853785753250122,
+      "learning_rate": 1.6188962973567068e-06,
+      "loss": 0.0563,
+      "step": 389
+    },
+    {
+      "epoch": 2.28717698683569,
+      "grad_norm": 0.26825377345085144,
+      "learning_rate": 1.5937642697167288e-06,
+      "loss": 0.062,
+      "step": 390
+    },
+    {
+      "epoch": 2.2930277913213066,
+      "grad_norm": 0.24329300224781036,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.0476,
+      "step": 391
+    },
+    {
+      "epoch": 2.2988785958069236,
+      "grad_norm": 0.23808631300926208,
+      "learning_rate": 1.5439800900357765e-06,
+      "loss": 0.0514,
+      "step": 392
+    },
+    {
+      "epoch": 2.30472940029254,
+      "grad_norm": 0.26007384061813354,
+      "learning_rate": 1.5193302701853674e-06,
+      "loss": 0.0478,
+      "step": 393
+    },
+    {
+      "epoch": 2.310580204778157,
+      "grad_norm": 0.3034699261188507,
+      "learning_rate": 1.4948435058510036e-06,
+      "loss": 0.0596,
+      "step": 394
+    },
+    {
+      "epoch": 2.316431009263774,
+      "grad_norm": 0.2601581811904907,
+      "learning_rate": 1.4705209441400841e-06,
+      "loss": 0.0529,
+      "step": 395
+    },
+    {
+      "epoch": 2.3222818137493904,
+      "grad_norm": 0.26665881276130676,
+      "learning_rate": 1.4463637244677648e-06,
+      "loss": 0.0516,
+      "step": 396
+    },
+    {
+      "epoch": 2.3281326182350073,
+      "grad_norm": 0.252401202917099,
+      "learning_rate": 1.422372978503589e-06,
+      "loss": 0.0568,
+      "step": 397
+    },
+    {
+      "epoch": 2.333983422720624,
+      "grad_norm": 0.2799394726753235,
+      "learning_rate": 1.3985498301184685e-06,
+      "loss": 0.0544,
+      "step": 398
+    },
+    {
+      "epoch": 2.3398342272062407,
+      "grad_norm": 0.29879605770111084,
+      "learning_rate": 1.374895395332037e-06,
+      "loss": 0.06,
+      "step": 399
+    },
+    {
+      "epoch": 2.3456850316918576,
+      "grad_norm": 0.27037307620048523,
+      "learning_rate": 1.351410782260366e-06,
+      "loss": 0.0601,
+      "step": 400
+    },
+    {
+      "epoch": 2.3515358361774745,
+      "grad_norm": 0.26528164744377136,
+      "learning_rate": 1.3280970910640573e-06,
+      "loss": 0.0547,
+      "step": 401
+    },
+    {
+      "epoch": 2.357386640663091,
+      "grad_norm": 0.3015322983264923,
+      "learning_rate": 1.3049554138967052e-06,
+      "loss": 0.0586,
+      "step": 402
+    },
+    {
+      "epoch": 2.363237445148708,
+      "grad_norm": 0.2491970807313919,
+      "learning_rate": 1.2819868348537263e-06,
+      "loss": 0.0492,
+      "step": 403
+    },
+    {
+      "epoch": 2.369088249634325,
+      "grad_norm": 0.262861967086792,
+      "learning_rate": 1.259192429921584e-06,
+      "loss": 0.0547,
+      "step": 404
+    },
+    {
+      "epoch": 2.3749390541199413,
+      "grad_norm": 0.2699519991874695,
+      "learning_rate": 1.2365732669273778e-06,
+      "loss": 0.0511,
+      "step": 405
+    },
+    {
+      "epoch": 2.3807898586055583,
+      "grad_norm": 0.30865174531936646,
+      "learning_rate": 1.2141304054888204e-06,
+      "loss": 0.0583,
+      "step": 406
+    },
+    {
+      "epoch": 2.386640663091175,
+      "grad_norm": 0.28503602743148804,
+      "learning_rate": 1.1918648969645947e-06,
+      "loss": 0.0615,
+      "step": 407
+    },
+    {
+      "epoch": 2.3924914675767917,
+      "grad_norm": 0.22828808426856995,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.0469,
+      "step": 408
+    },
+    {
+      "epoch": 2.3983422720624086,
+      "grad_norm": 0.28332284092903137,
+      "learning_rate": 1.1478701025036359e-06,
+      "loss": 0.0581,
+      "step": 409
+    },
+    {
+      "epoch": 2.4041930765480255,
+      "grad_norm": 0.2843197286128998,
+      "learning_rate": 1.126142877547826e-06,
+      "loss": 0.0633,
+      "step": 410
+    },
+    {
+      "epoch": 2.410043881033642,
+      "grad_norm": 0.2659061849117279,
+      "learning_rate": 1.1045971273716476e-06,
+      "loss": 0.0522,
+      "step": 411
+    },
+    {
+      "epoch": 2.415894685519259,
+      "grad_norm": 0.28145578503608704,
+      "learning_rate": 1.083233861307697e-06,
+      "loss": 0.0598,
+      "step": 412
+    },
+    {
+      "epoch": 2.421745490004876,
+      "grad_norm": 0.29039686918258667,
+      "learning_rate": 1.062054080139916e-06,
+      "loss": 0.0585,
+      "step": 413
+    },
+    {
+      "epoch": 2.4275962944904923,
+      "grad_norm": 0.2717377543449402,
+      "learning_rate": 1.0410587760567104e-06,
+      "loss": 0.0556,
+      "step": 414
+    },
+    {
+      "epoch": 2.4334470989761092,
+      "grad_norm": 0.283588171005249,
+      "learning_rate": 1.0202489326044663e-06,
+      "loss": 0.0586,
+      "step": 415
+    },
+    {
+      "epoch": 2.439297903461726,
+      "grad_norm": 0.2644156515598297,
+      "learning_rate": 9.99625524641481e-07,
+      "loss": 0.0519,
+      "step": 416
+    },
+    {
+      "epoch": 2.4451487079473426,
+      "grad_norm": 0.28385522961616516,
+      "learning_rate": 9.791895182922911e-07,
+      "loss": 0.0584,
+      "step": 417
+    },
+    {
+      "epoch": 2.4509995124329595,
+      "grad_norm": 0.2593843340873718,
+      "learning_rate": 9.589418709024146e-07,
+      "loss": 0.0582,
+      "step": 418
+    },
+    {
+      "epoch": 2.4568503169185765,
+      "grad_norm": 0.28470900654792786,
+      "learning_rate": 9.388835309934985e-07,
+      "loss": 0.0651,
+      "step": 419
+    },
+    {
+      "epoch": 2.462701121404193,
+      "grad_norm": 0.23977982997894287,
+      "learning_rate": 9.190154382188921e-07,
+      "loss": 0.0511,
+      "step": 420
+    },
+    {
+      "epoch": 2.46855192588981,
+      "grad_norm": 0.2712235152721405,
+      "learning_rate": 8.993385233196223e-07,
+      "loss": 0.0545,
+      "step": 421
+    },
+    {
+      "epoch": 2.474402730375427,
+      "grad_norm": 0.256510466337204,
+      "learning_rate": 8.79853708080795e-07,
+      "loss": 0.0563,
+      "step": 422
+    },
+    {
+      "epoch": 2.4802535348610433,
+      "grad_norm": 0.27964967489242554,
+      "learning_rate": 8.605619052884106e-07,
+      "loss": 0.0634,
+      "step": 423
+    },
+    {
+      "epoch": 2.48610433934666,
+      "grad_norm": 0.2607182264328003,
+      "learning_rate": 8.414640186866063e-07,
+      "loss": 0.0455,
+      "step": 424
+    },
+    {
+      "epoch": 2.491955143832277,
+      "grad_norm": 0.28515201807022095,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.0582,
+      "step": 425
+    },
+    {
+      "epoch": 2.4978059483178936,
+      "grad_norm": 0.29618608951568604,
+      "learning_rate": 8.03853563568367e-07,
+      "loss": 0.0615,
+      "step": 426
+    },
+    {
+      "epoch": 2.5036567528035105,
+      "grad_norm": 0.30800962448120117,
+      "learning_rate": 7.8534275695198e-07,
+      "loss": 0.0654,
+      "step": 427
+    },
+    {
+      "epoch": 2.509507557289127,
+      "grad_norm": 0.29063132405281067,
+      "learning_rate": 7.670293902437331e-07,
+      "loss": 0.0566,
+      "step": 428
+    },
+    {
+      "epoch": 2.515358361774744,
+      "grad_norm": 0.28903132677078247,
+      "learning_rate": 7.489143213519301e-07,
+      "loss": 0.0635,
+      "step": 429
+    },
+    {
+      "epoch": 2.521209166260361,
+      "grad_norm": 0.2604012191295624,
+      "learning_rate": 7.309983988954078e-07,
+      "loss": 0.0502,
+      "step": 430
+    },
+    {
+      "epoch": 2.5270599707459773,
+      "grad_norm": 0.30102649331092834,
+      "learning_rate": 7.132824621637891e-07,
+      "loss": 0.057,
+      "step": 431
+    },
+    {
+      "epoch": 2.5329107752315942,
+      "grad_norm": 0.2743903696537018,
+      "learning_rate": 6.957673410781617e-07,
+      "loss": 0.0458,
+      "step": 432
+    },
+    {
+      "epoch": 2.538761579717211,
+      "grad_norm": 0.30411839485168457,
+      "learning_rate": 6.784538561521986e-07,
+      "loss": 0.0696,
+      "step": 433
+    },
+    {
+      "epoch": 2.5446123842028276,
+      "grad_norm": 0.26881927251815796,
+      "learning_rate": 6.613428184537235e-07,
+      "loss": 0.0585,
+      "step": 434
+    },
+    {
+      "epoch": 2.5504631886884446,
+      "grad_norm": 0.2715945541858673,
+      "learning_rate": 6.444350295667112e-07,
+      "loss": 0.0506,
+      "step": 435
+    },
+    {
+      "epoch": 2.5563139931740615,
+      "grad_norm": 0.27122291922569275,
+      "learning_rate": 6.277312815537423e-07,
+      "loss": 0.0548,
+      "step": 436
+    },
+    {
+      "epoch": 2.562164797659678,
+      "grad_norm": 0.30401352047920227,
+      "learning_rate": 6.112323569188927e-07,
+      "loss": 0.0536,
+      "step": 437
+    },
+    {
+      "epoch": 2.568015602145295,
+      "grad_norm": 0.24554386734962463,
+      "learning_rate": 5.949390285710777e-07,
+      "loss": 0.0519,
+      "step": 438
+    },
+    {
+      "epoch": 2.573866406630912,
+      "grad_norm": 0.27577313780784607,
+      "learning_rate": 5.788520597878477e-07,
+      "loss": 0.0529,
+      "step": 439
+    },
+    {
+      "epoch": 2.5797172111165283,
+      "grad_norm": 0.3495662212371826,
+      "learning_rate": 5.629722041796292e-07,
+      "loss": 0.0569,
+      "step": 440
+    },
+    {
+      "epoch": 2.585568015602145,
+      "grad_norm": 0.2668460011482239,
+      "learning_rate": 5.473002056544191e-07,
+      "loss": 0.0453,
+      "step": 441
+    },
+    {
+      "epoch": 2.591418820087762,
+      "grad_norm": 0.2764504551887512,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.0573,
+      "step": 442
+    },
+    {
+      "epoch": 2.5972696245733786,
+      "grad_norm": 0.2935810983181,
+      "learning_rate": 5.165827067642415e-07,
+      "loss": 0.0495,
+      "step": 443
+    },
+    {
+      "epoch": 2.6031204290589955,
+      "grad_norm": 0.2925431728363037,
+      "learning_rate": 5.015386453917742e-07,
+      "loss": 0.0535,
+      "step": 444
+    },
+    {
+      "epoch": 2.6089712335446125,
+      "grad_norm": 0.2892134487628937,
+      "learning_rate": 4.867053190199011e-07,
+      "loss": 0.0607,
+      "step": 445
+    },
+    {
+      "epoch": 2.614822038030229,
+      "grad_norm": 0.28982144594192505,
+      "learning_rate": 4.720834225308962e-07,
+      "loss": 0.0612,
+      "step": 446
+    },
+    {
+      "epoch": 2.620672842515846,
+      "grad_norm": 0.24418623745441437,
+      "learning_rate": 4.576736409023813e-07,
+      "loss": 0.051,
+      "step": 447
+    },
+    {
+      "epoch": 2.626523647001463,
+      "grad_norm": 0.26711544394493103,
+      "learning_rate": 4.4347664917524293e-07,
+      "loss": 0.0598,
+      "step": 448
+    },
+    {
+      "epoch": 2.6323744514870793,
+      "grad_norm": 0.28195297718048096,
+      "learning_rate": 4.29493112422007e-07,
+      "loss": 0.0546,
+      "step": 449
+    },
+    {
+      "epoch": 2.638225255972696,
+      "grad_norm": 0.29547280073165894,
+      "learning_rate": 4.15723685715686e-07,
+      "loss": 0.0535,
+      "step": 450
+    },
+    {
+      "epoch": 2.644076060458313,
+      "grad_norm": 0.2511988878250122,
+      "learning_rate": 4.0216901409908695e-07,
+      "loss": 0.0509,
+      "step": 451
+    },
+    {
+      "epoch": 2.6499268649439296,
+      "grad_norm": 0.28745976090431213,
+      "learning_rate": 3.8882973255459975e-07,
+      "loss": 0.0502,
+      "step": 452
+    },
+    {
+      "epoch": 2.6557776694295465,
+      "grad_norm": 0.2565235495567322,
+      "learning_rate": 3.7570646597444196e-07,
+      "loss": 0.0477,
+      "step": 453
+    },
+    {
+      "epoch": 2.6616284739151634,
+      "grad_norm": 0.29118213057518005,
+      "learning_rate": 3.627998291313939e-07,
+      "loss": 0.0669,
+      "step": 454
+    },
+    {
+      "epoch": 2.66747927840078,
+      "grad_norm": 0.29614195227622986,
+      "learning_rate": 3.5011042664999663e-07,
+      "loss": 0.0574,
+      "step": 455
+    },
+    {
+      "epoch": 2.673330082886397,
+      "grad_norm": 0.25614967942237854,
+      "learning_rate": 3.3763885297822153e-07,
+      "loss": 0.0588,
+      "step": 456
+    },
+    {
+      "epoch": 2.6791808873720138,
+      "grad_norm": 0.27203789353370667,
+      "learning_rate": 3.2538569235963216e-07,
+      "loss": 0.0508,
+      "step": 457
+    },
+    {
+      "epoch": 2.6850316918576302,
+      "grad_norm": 0.26867544651031494,
+      "learning_rate": 3.133515188060077e-07,
+      "loss": 0.055,
+      "step": 458
+    },
+    {
+      "epoch": 2.690882496343247,
+      "grad_norm": 0.28810831904411316,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.0602,
+      "step": 459
+    },
+    {
+      "epoch": 2.696733300828864,
+      "grad_norm": 0.28718477487564087,
+      "learning_rate": 2.899423776210092e-07,
+      "loss": 0.0625,
+      "step": 460
+    },
+    {
+      "epoch": 2.7025841053144806,
+      "grad_norm": 0.2641659379005432,
+      "learning_rate": 2.785685066146776e-07,
+      "loss": 0.057,
+      "step": 461
+    },
+    {
+      "epoch": 2.7084349098000975,
+      "grad_norm": 0.3124268352985382,
+      "learning_rate": 2.6741581587202747e-07,
+      "loss": 0.0567,
+      "step": 462
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.26910921931266785,
+      "learning_rate": 2.5648482785220865e-07,
+      "loss": 0.0603,
+      "step": 463
+    },
+    {
+      "epoch": 2.720136518771331,
+      "grad_norm": 0.26910898089408875,
+      "learning_rate": 2.4577605462847764e-07,
+      "loss": 0.0575,
+      "step": 464
+    },
+    {
+      "epoch": 2.725987323256948,
+      "grad_norm": 0.2963363230228424,
+      "learning_rate": 2.3528999786421758e-07,
+      "loss": 0.0556,
+      "step": 465
+    },
+    {
+      "epoch": 2.7318381277425647,
+      "grad_norm": 0.2956644892692566,
+      "learning_rate": 2.25027148789429e-07,
+      "loss": 0.0594,
+      "step": 466
+    },
+    {
+      "epoch": 2.737688932228181,
+      "grad_norm": 0.26555967330932617,
+      "learning_rate": 2.1498798817772281e-07,
+      "loss": 0.059,
+      "step": 467
+    },
+    {
+      "epoch": 2.743539736713798,
+      "grad_norm": 0.2682870626449585,
+      "learning_rate": 2.0517298632379445e-07,
+      "loss": 0.0531,
+      "step": 468
+    },
+    {
+      "epoch": 2.749390541199415,
+      "grad_norm": 0.2852657437324524,
+      "learning_rate": 1.9558260302139642e-07,
+      "loss": 0.0498,
+      "step": 469
+    },
+    {
+      "epoch": 2.7552413456850315,
+      "grad_norm": 0.27579066157341003,
+      "learning_rate": 1.8621728754179392e-07,
+      "loss": 0.0621,
+      "step": 470
+    },
+    {
+      "epoch": 2.7610921501706485,
+      "grad_norm": 0.29085394740104675,
+      "learning_rate": 1.770774786127244e-07,
+      "loss": 0.0575,
+      "step": 471
+    },
+    {
+      "epoch": 2.7669429546562654,
+      "grad_norm": 0.2594444155693054,
+      "learning_rate": 1.6816360439783797e-07,
+      "loss": 0.0522,
+      "step": 472
+    },
+    {
+      "epoch": 2.772793759141882,
+      "grad_norm": 0.292959600687027,
+      "learning_rate": 1.5947608247664558e-07,
+      "loss": 0.0563,
+      "step": 473
+    },
+    {
+      "epoch": 2.778644563627499,
+      "grad_norm": 0.2607786953449249,
+      "learning_rate": 1.510153198249531e-07,
+      "loss": 0.0505,
+      "step": 474
+    },
+    {
+      "epoch": 2.7844953681131157,
+      "grad_norm": 0.285178542137146,
+      "learning_rate": 1.4278171279579757e-07,
+      "loss": 0.0601,
+      "step": 475
+    },
+    {
+      "epoch": 2.790346172598732,
+      "grad_norm": 0.28294607996940613,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.0539,
+      "step": 476
+    },
+    {
+      "epoch": 2.796196977084349,
+      "grad_norm": 0.29305973649024963,
+      "learning_rate": 1.2699749779249926e-07,
+      "loss": 0.0648,
+      "step": 477
+    },
+    {
+      "epoch": 2.802047781569966,
+      "grad_norm": 0.2848883867263794,
+      "learning_rate": 1.1944762924597286e-07,
+      "loss": 0.0596,
+      "step": 478
+    },
+    {
+      "epoch": 2.8078985860555825,
+      "grad_norm": 0.27572354674339294,
+      "learning_rate": 1.1212639514257829e-07,
+      "loss": 0.0545,
+      "step": 479
+    },
+    {
+      "epoch": 2.8137493905411994,
+      "grad_norm": 0.2800915539264679,
+      "learning_rate": 1.0503413845297739e-07,
+      "loss": 0.0586,
+      "step": 480
+    },
+    {
+      "epoch": 2.8196001950268164,
+      "grad_norm": 0.27929428219795227,
+      "learning_rate": 9.817119142115472e-08,
+      "loss": 0.0535,
+      "step": 481
+    },
+    {
+      "epoch": 2.825450999512433,
+      "grad_norm": 0.29202061891555786,
+      "learning_rate": 9.15378755488483e-08,
+      "loss": 0.0677,
+      "step": 482
+    },
+    {
+      "epoch": 2.8313018039980498,
+      "grad_norm": 0.2733800411224365,
+      "learning_rate": 8.513450158049109e-08,
+      "loss": 0.057,
+      "step": 483
+    },
+    {
+      "epoch": 2.8371526084836667,
+      "grad_norm": 0.27349552512168884,
+      "learning_rate": 7.896136948865429e-08,
+      "loss": 0.0595,
+      "step": 484
+    },
+    {
+      "epoch": 2.843003412969283,
+      "grad_norm": 0.3204438388347626,
+      "learning_rate": 7.301876845999368e-08,
+      "loss": 0.0638,
+      "step": 485
+    },
+    {
+      "epoch": 2.8488542174549,
+      "grad_norm": 0.2688818573951721,
+      "learning_rate": 6.730697688170251e-08,
+      "loss": 0.0514,
+      "step": 486
+    },
+    {
+      "epoch": 2.854705021940517,
+      "grad_norm": 0.27996474504470825,
+      "learning_rate": 6.182626232847044e-08,
+      "loss": 0.06,
+      "step": 487
+    },
+    {
+      "epoch": 2.8605558264261335,
+      "grad_norm": 0.28294089436531067,
+      "learning_rate": 5.6576881549949e-08,
+      "loss": 0.0476,
+      "step": 488
+    },
+    {
+      "epoch": 2.8664066309117504,
+      "grad_norm": 0.26451075077056885,
+      "learning_rate": 5.155908045872349e-08,
+      "loss": 0.0587,
+      "step": 489
+    },
+    {
+      "epoch": 2.8722574353973673,
+      "grad_norm": 0.28928130865097046,
+      "learning_rate": 4.677309411879327e-08,
+      "loss": 0.0518,
+      "step": 490
+    },
+    {
+      "epoch": 2.878108239882984,
+      "grad_norm": 0.2694530487060547,
+      "learning_rate": 4.221914673455896e-08,
+      "loss": 0.0541,
+      "step": 491
+    },
+    {
+      "epoch": 2.8839590443686007,
+      "grad_norm": 0.3015761077404022,
+      "learning_rate": 3.7897451640321326e-08,
+      "loss": 0.0602,
+      "step": 492
+    },
+    {
+      "epoch": 2.8898098488542177,
+      "grad_norm": 0.2916721999645233,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.0565,
+      "step": 493
+    },
+    {
+      "epoch": 2.895660653339834,
+      "grad_norm": 0.2948850989341736,
+      "learning_rate": 2.995161724907658e-08,
+      "loss": 0.0619,
+      "step": 494
+    },
+    {
+      "epoch": 2.901511457825451,
+      "grad_norm": 0.310370534658432,
+      "learning_rate": 2.6327850182769065e-08,
+      "loss": 0.0604,
+      "step": 495
+    },
+    {
+      "epoch": 2.907362262311068,
+      "grad_norm": 0.2993476092815399,
+      "learning_rate": 2.29370798504186e-08,
+      "loss": 0.0581,
+      "step": 496
+    },
+    {
+      "epoch": 2.9132130667966845,
+      "grad_norm": 0.2968423366546631,
+      "learning_rate": 1.9779465096112505e-08,
+      "loss": 0.0571,
+      "step": 497
+    },
+    {
+      "epoch": 2.9190638712823014,
+      "grad_norm": 0.2754110097885132,
+      "learning_rate": 1.6855153841527915e-08,
+      "loss": 0.0585,
+      "step": 498
+    },
+    {
+      "epoch": 2.9249146757679183,
+      "grad_norm": 0.28342047333717346,
+      "learning_rate": 1.4164283079001196e-08,
+      "loss": 0.0567,
+      "step": 499
+    },
+    {
+      "epoch": 2.930765480253535,
+      "grad_norm": 0.2792755961418152,
+      "learning_rate": 1.1706978865113072e-08,
+      "loss": 0.0497,
+      "step": 500
+    },
+    {
+      "epoch": 2.9366162847391517,
+      "grad_norm": 0.3103918135166168,
+      "learning_rate": 9.48335631477948e-09,
+      "loss": 0.0637,
+      "step": 501
+    },
+    {
+      "epoch": 2.9424670892247686,
+      "grad_norm": 0.2594921588897705,
+      "learning_rate": 7.49351959586253e-09,
+      "loss": 0.0587,
+      "step": 502
+    },
+    {
+      "epoch": 2.948317893710385,
+      "grad_norm": 0.2774949371814728,
+      "learning_rate": 5.737561924288315e-09,
+      "loss": 0.0536,
+      "step": 503
+    },
+    {
+      "epoch": 2.954168698196002,
+      "grad_norm": 0.3025616407394409,
+      "learning_rate": 4.2155655596809455e-09,
+      "loss": 0.0559,
+      "step": 504
+    },
+    {
+      "epoch": 2.960019502681619,
+      "grad_norm": 0.2954673767089844,
+      "learning_rate": 2.9276018015089725e-09,
+      "loss": 0.0669,
+      "step": 505
+    },
+    {
+      "epoch": 2.9658703071672354,
+      "grad_norm": 0.2557486295700073,
+      "learning_rate": 1.8737309857463916e-09,
+      "loss": 0.0663,
+      "step": 506
+    },
+    {
+      "epoch": 2.9717211116528524,
+      "grad_norm": 0.29354172945022583,
+      "learning_rate": 1.054002482043237e-09,
+      "loss": 0.0623,
+      "step": 507
+    },
+    {
+      "epoch": 2.9775719161384693,
+      "grad_norm": 0.3089665174484253,
+      "learning_rate": 4.684546914163201e-10,
+      "loss": 0.054,
+      "step": 508
+    },
+    {
+      "epoch": 2.9834227206240858,
+      "grad_norm": 0.3170253038406372,
+      "learning_rate": 1.1711504444733567e-10,
+      "loss": 0.0626,
+      "step": 509
+    },
+    {
+      "epoch": 2.9892735251097027,
+      "grad_norm": 0.2732970118522644,
+      "learning_rate": 0.0,
+      "loss": 0.0551,
+      "step": 510
+    },
+    {
+      "epoch": 2.9892735251097027,
+      "step": 510,
+      "total_flos": 1494941780148224.0,
+      "train_loss": 0.029626486676872944,
+      "train_runtime": 67167.8945,
+      "train_samples_per_second": 0.733,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "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": 1494941780148224.0,
+  "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 sha256:6897fe15ebfcec7e006f6f475f7a65c74c8d3288c5be27ccaff0c77b1b2b4ef5
+size 7480