Add HuggingFaceH4/starcoder2-15b-ift-v5.0 checkpoint

README.md

@@ -0,0 +1,71 @@
+---
+license: bigcode-openrail-m
+base_model: bigcode/starcoder2-15b
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/airoboros-3.2
+- HuggingFaceH4/Code-Feedback
+- HuggingFaceH4/orca-math-word-problems-200k
+- HuggingFaceH4/SystemChat
+- HuggingFaceH4/capybara
+model-index:
+- name: starcoder2-15b-sft-v5.0
+  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. -->
+
+# starcoder2-15b-sft-v5.0
+
+This model is a fine-tuned version of [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b) on the HuggingFaceH4/airoboros-3.2, the HuggingFaceH4/Code-Feedback, the HuggingFaceH4/orca-math-word-problems-200k, the HuggingFaceH4/SystemChat and the HuggingFaceH4/capybara datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.6614
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6422        | 1.0   | 910  | 0.6910          |
+| 0.5701        | 2.0   | 1820 | 0.6639          |
+| 0.5227        | 3.0   | 2730 | 0.6614          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 49153,
+  "<|im_start|>": 49152
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6613607406616211,
+    "eval_runtime": 13.2548,
+    "eval_samples": 3200,
+    "eval_samples_per_second": 103.962,
+    "eval_steps_per_second": 0.83,
+    "perplexity": 1.9374268770613925,
+    "train_loss": 0.6159939037574517,
+    "train_runtime": 13745.4884,
+    "train_samples": 344926,
+    "train_samples_per_second": 25.399,
+    "train_steps_per_second": 0.199
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bigcode/starcoder2-15b",
+  "architectures": [
+    "Starcoder2ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 6144,
+  "initializer_range": 0.01275,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "residual_dropout": 0.1,
+  "rope_theta": 100000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49154
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6613607406616211,
+    "eval_runtime": 13.2548,
+    "eval_samples": 3200,
+    "eval_samples_per_second": 103.962,
+    "eval_steps_per_second": 0.83,
+    "perplexity": 1.9374268770613925
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d42fbff705dc05edbb65f0ae3f51df701209be99287e4475dbe9399dc6fe18
+size 4908132312

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2e3ca209549ff47ede1f0c26ca18dbc993337298eb2d82caaef7b637b52d43
+size 4996327240

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7230487178cdba324781f21e3be5fc6d858b752370c353877074e49c423cf7a
+size 4983729152

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab59837a2010f9d57928176bcc8953efa3d372d5e31229b29cdfa5d773eb374e
+size 4996327312

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3fea31b72aed8d39bf1adf512f9fba77f05669cface5ccbf12badc06ede4fa3
+size 4983729152

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee54a75dde9875e171ccc6ea270d84b97c131b1bfff843e4f3ffa5f0cdc95904
+size 4996327312

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dedf79db5b5196be63a2259994515677bc831d8ccd10e9db4b3af671029533a
+size 2051327128

model.safetensors.index.json

@@ -0,0 +1,651 @@
+{
+  "metadata": {
+    "total_size": 31915827200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.25.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
+    "model.layers.31.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
+    "model.layers.31.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.31.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.32.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.input_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.38.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.c_fc.bias": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.c_fc.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.c_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.38.mlp.c_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.39.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.c_fc.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.c_fc.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.c_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.mlp.c_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.bias": "model-00007-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

runs/Mar08_16-17-47_ip-26-0-163-147/events.out.tfevents.1709915296.ip-26-0-163-147.1763548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24061e05cb68d6656fbeb9eb97ee71ee770a76a889dd2de54d31416ab4be7fb
+size 48612

runs/Mar08_18-36-38_ip-26-0-168-30/events.out.tfevents.1709923104.ip-26-0-168-30.2820495.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a128747e9ca38ebb9f652d6bfcc35609a3704100ee7136628845688db499ca8
+size 121669

runs/Mar08_18-36-38_ip-26-0-168-30/events.out.tfevents.1709936860.ip-26-0-168-30.2820495.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc59d04e0191824a5384f445688fada1eb5c0d96b64d6cf16f987ea3a59c036
+size 359

runs/Mar08_21-16-43_ip-26-0-167-51/events.out.tfevents.1709932888.ip-26-0-167-51.328029.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e720988e253cc7002ac1208eb083ffc6ea48b692b88c73942a5eef1316c567e7
+size 121675

runs/Mar08_21-16-43_ip-26-0-167-51/events.out.tfevents.1709947427.ip-26-0-167-51.328029.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3700a1edbdcdc5461f727c9d730c803256940d83832e91f12f86fb66eefdfbb4
+size 359

runs/Mar08_21-26-05_ip-26-0-172-252/events.out.tfevents.1709933435.ip-26-0-172-252.2556335.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a3a24f07c116fd409201790c225ff8683a1873000482bb3a6f9fecdf279b69
+size 121676

runs/Mar08_21-26-05_ip-26-0-172-252/events.out.tfevents.1709948930.ip-26-0-172-252.2556335.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e3d2bfe0d255a910f40f3de7b9741ee01d4bae81abd095b372e859438a7591
+size 359

runs/Mar08_21-27-27_ip-26-0-164-18/events.out.tfevents.1709933533.ip-26-0-164-18.2014308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3724ac8cf023d7f9cf0d60367c2b56665b4cb7965c5d71ac7b6f01b68d6c881
+size 6851

runs/Mar08_21-56-54_ip-26-0-173-121/events.out.tfevents.1709935115.ip-26-0-173-121.311205.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732012a5b451b4dc3c09e3f9e6da60d77431dc2e6bdb26f517ce9996490549a6
+size 43705

runs/Mar08_22-00-45_ip-26-0-160-225/events.out.tfevents.1709935775.ip-26-0-160-225.445184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8624fdfb6f00df7fe679aec6f633f7525560285ff2c730f99b7709c2ea584328
+size 88121

runs/Mar08_22-00-45_ip-26-0-160-225/events.out.tfevents.1709945594.ip-26-0-160-225.445184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd37bef74b6698bfd2641bc8aaa9eed0c625d9397c91722a24410999170c0cd
+size 359

runs/Mar08_22-17-01_ip-26-0-163-58/events.out.tfevents.1709936545.ip-26-0-163-58.306463.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2c8cab80a21f3cf0c981a8985a7b4d6625f4f4a0ff7430e7de7fd20e95adf4
+size 47819

runs/Mar08_22-17-01_ip-26-0-163-58/events.out.tfevents.1709941542.ip-26-0-163-58.306463.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b0f1a101a4b7977d1de0df75343f7c71f396cdf2c49560e3d1a4eda4b1326d
+size 359

runs/Mar08_22-18-04_ip-26-0-170-31/events.out.tfevents.1709936621.ip-26-0-170-31.2209735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0fb10f88bfb5df46fb61c7d31ec283bebd3759d9aa8e808f0762220382f510
+size 61112

runs/Mar08_22-18-04_ip-26-0-170-31/events.out.tfevents.1709943158.ip-26-0-170-31.2209735.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4fdb51d0bd9d9cd85bf1f5aac72cbc0479429be30b8588e9af2b0e44b9969e
+size 359

runs/Mar08_22-30-40_ip-26-0-168-30/events.out.tfevents.1709938809.ip-26-0-168-30.2846469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79eacd641094ccd84cdd1f6ba319a33f2fa7d14a1e3486054869e0f7f15414bc
+size 121669

runs/Mar08_22-30-40_ip-26-0-168-30/events.out.tfevents.1709952568.ip-26-0-168-30.2846469.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f09c606bb91a6cfd91a47ea08860441f57e4769fc0e2ee45db23322832e1b41
+size 359

runs/Mar08_23-28-10_ip-26-0-173-121/events.out.tfevents.1709940599.ip-26-0-173-121.320213.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5501f78dae58ae3d318b6de03478ef93ffa5e11b9c1a23e2e4f0e42bec0df9
+size 43705

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,338 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<code_to_intermediate>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<intermediate_to_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<pr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<pr_status>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "<pr_is_merged>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<pr_base>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "<pr_file>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<pr_base_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "<pr_diff>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<pr_diff_hunk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pr_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "27": {
+      "content": "<pr_event_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28": {
+      "content": "<pr_review>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29": {
+      "content": "<pr_review_state>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<pr_review_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "<pr_in_reply_to_review_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<pr_in_reply_to_comment_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "<pr_diff_hunk_comment_line>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "<NAME>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "<EMAIL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "content": "<KEY>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "37": {
+      "content": "<PASSWORD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6159939037574517,
+    "train_runtime": 13745.4884,
+    "train_samples": 344926,
+    "train_samples_per_second": 25.399,
+    "train_steps_per_second": 0.199
+}

trainer_state.json

@@ -0,0 +1,3883 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2730,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.5403712464892836,
+      "learning_rate": 7.326007326007327e-08,
+      "loss": 1.379,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.5059454164116177,
+      "learning_rate": 3.6630036630036635e-07,
+      "loss": 1.411,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.403039830631443,
+      "learning_rate": 7.326007326007327e-07,
+      "loss": 1.3904,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.187796179583603,
+      "learning_rate": 1.098901098901099e-06,
+      "loss": 1.3698,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.4489435205825498,
+      "learning_rate": 1.4652014652014654e-06,
+      "loss": 1.2609,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.483113856101743,
+      "learning_rate": 1.8315018315018316e-06,
+      "loss": 1.1341,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7051067484479403,
+      "learning_rate": 2.197802197802198e-06,
+      "loss": 1.0478,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7254079611231652,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 1.0312,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6389491910662315,
+      "learning_rate": 2.930402930402931e-06,
+      "loss": 0.9897,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.500844994643637,
+      "learning_rate": 3.2967032967032968e-06,
+      "loss": 0.9549,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.4201833928940666,
+      "learning_rate": 3.663003663003663e-06,
+      "loss": 0.9373,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.370974019020061,
+      "learning_rate": 4.0293040293040296e-06,
+      "loss": 0.9118,
+      "step": 55
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.34743939582124356,
+      "learning_rate": 4.395604395604396e-06,
+      "loss": 0.8832,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.30550288282826443,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.8905,
+      "step": 65
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3877890435103539,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 0.8745,
+      "step": 70
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4090389705350457,
+      "learning_rate": 5.494505494505495e-06,
+      "loss": 0.869,
+      "step": 75
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.28471599620620913,
+      "learning_rate": 5.860805860805862e-06,
+      "loss": 0.8701,
+      "step": 80
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2835464196942085,
+      "learning_rate": 6.227106227106228e-06,
+      "loss": 0.8566,
+      "step": 85
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3339230231336609,
+      "learning_rate": 6.5934065934065935e-06,
+      "loss": 0.8926,
+      "step": 90
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.26409030663411054,
+      "learning_rate": 6.95970695970696e-06,
+      "loss": 0.8639,
+      "step": 95
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2548657900119433,
+      "learning_rate": 7.326007326007326e-06,
+      "loss": 0.8574,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.33583619074613247,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.8371,
+      "step": 105
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.26284318740686946,
+      "learning_rate": 8.058608058608059e-06,
+      "loss": 0.8209,
+      "step": 110
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.27047354400674645,
+      "learning_rate": 8.424908424908426e-06,
+      "loss": 0.8125,
+      "step": 115
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.25311492465959046,
+      "learning_rate": 8.791208791208792e-06,
+      "loss": 0.8371,
+      "step": 120
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.27273984018778547,
+      "learning_rate": 9.157509157509158e-06,
+      "loss": 0.8361,
+      "step": 125
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.2789308175031694,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.7995,
+      "step": 130
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.26030914277390094,
+      "learning_rate": 9.890109890109892e-06,
+      "loss": 0.8137,
+      "step": 135
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.8625694710794981,
+      "learning_rate": 1.0256410256410256e-05,
+      "loss": 0.7968,
+      "step": 140
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.26526694267370393,
+      "learning_rate": 1.0622710622710623e-05,
+      "loss": 0.8011,
+      "step": 145
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2786629865850713,
+      "learning_rate": 1.098901098901099e-05,
+      "loss": 0.7944,
+      "step": 150
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2547160983307644,
+      "learning_rate": 1.1355311355311356e-05,
+      "loss": 0.8072,
+      "step": 155
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.252471949121061,
+      "learning_rate": 1.1721611721611723e-05,
+      "loss": 0.7941,
+      "step": 160
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.25858945532947464,
+      "learning_rate": 1.2087912087912089e-05,
+      "loss": 0.7951,
+      "step": 165
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.247980244139678,
+      "learning_rate": 1.2454212454212456e-05,
+      "loss": 0.7858,
+      "step": 170
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.255903929999623,
+      "learning_rate": 1.2820512820512823e-05,
+      "loss": 0.7878,
+      "step": 175
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6019780019252425,
+      "learning_rate": 1.3186813186813187e-05,
+      "loss": 0.7795,
+      "step": 180
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.27779059252699495,
+      "learning_rate": 1.3553113553113554e-05,
+      "loss": 0.7754,
+      "step": 185
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2710280200562755,
+      "learning_rate": 1.391941391941392e-05,
+      "loss": 0.7855,
+      "step": 190
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2743116770469599,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.7565,
+      "step": 195
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.26037793315040886,
+      "learning_rate": 1.4652014652014653e-05,
+      "loss": 0.7726,
+      "step": 200
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.26090200965795596,
+      "learning_rate": 1.501831501831502e-05,
+      "loss": 0.7653,
+      "step": 205
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.2632394726032374,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.777,
+      "step": 210
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2540381175124688,
+      "learning_rate": 1.575091575091575e-05,
+      "loss": 0.7433,
+      "step": 215
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2627604876525692,
+      "learning_rate": 1.6117216117216118e-05,
+      "loss": 0.7597,
+      "step": 220
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2651216093866056,
+      "learning_rate": 1.6483516483516486e-05,
+      "loss": 0.7609,
+      "step": 225
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.24401238946000964,
+      "learning_rate": 1.6849816849816853e-05,
+      "loss": 0.7469,
+      "step": 230
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2547534354636469,
+      "learning_rate": 1.721611721611722e-05,
+      "loss": 0.7641,
+      "step": 235
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.24893607597108447,
+      "learning_rate": 1.7582417582417584e-05,
+      "loss": 0.7323,
+      "step": 240
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2530974475033568,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 0.7533,
+      "step": 245
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2733773460887857,
+      "learning_rate": 1.8315018315018315e-05,
+      "loss": 0.7538,
+      "step": 250
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.27130243796420767,
+      "learning_rate": 1.8681318681318682e-05,
+      "loss": 0.7665,
+      "step": 255
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.25889603349835133,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.737,
+      "step": 260
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.2758988715664599,
+      "learning_rate": 1.9413919413919417e-05,
+      "loss": 0.7587,
+      "step": 265
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.24591163232882832,
+      "learning_rate": 1.9780219780219784e-05,
+      "loss": 0.7503,
+      "step": 270
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.29213859652031626,
+      "learning_rate": 1.9999967302150437e-05,
+      "loss": 0.7544,
+      "step": 275
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.23841997418474895,
+      "learning_rate": 1.9999599453798523e-05,
+      "loss": 0.738,
+      "step": 280
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.23103339591842176,
+      "learning_rate": 1.9998822899867633e-05,
+      "loss": 0.7316,
+      "step": 285
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.24038013908936962,
+      "learning_rate": 1.9997637672097222e-05,
+      "loss": 0.7202,
+      "step": 290
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.24246381579537735,
+      "learning_rate": 1.9996043818930153e-05,
+      "loss": 0.7463,
+      "step": 295
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.24527189059683477,
+      "learning_rate": 1.9994041405510705e-05,
+      "loss": 0.755,
+      "step": 300
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.24371499098074792,
+      "learning_rate": 1.999163051368191e-05,
+      "loss": 0.7599,
+      "step": 305
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2575400741876107,
+      "learning_rate": 1.9988811241982206e-05,
+      "loss": 0.7443,
+      "step": 310
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.2404592716601957,
+      "learning_rate": 1.9985583705641418e-05,
+      "loss": 0.7327,
+      "step": 315
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.24637921462827092,
+      "learning_rate": 1.9981948036576045e-05,
+      "loss": 0.7339,
+      "step": 320
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.24681007900489016,
+      "learning_rate": 1.997790438338385e-05,
+      "loss": 0.7265,
+      "step": 325
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2690257655867855,
+      "learning_rate": 1.997345291133783e-05,
+      "loss": 0.7232,
+      "step": 330
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2534124946734991,
+      "learning_rate": 1.9968593802379405e-05,
+      "loss": 0.7327,
+      "step": 335
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.23796973039683816,
+      "learning_rate": 1.9963327255111033e-05,
+      "loss": 0.7218,
+      "step": 340
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.23546876853519053,
+      "learning_rate": 1.9957653484788054e-05,
+      "loss": 0.7291,
+      "step": 345
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.2629306598176605,
+      "learning_rate": 1.9951572723309918e-05,
+      "loss": 0.7177,
+      "step": 350
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.2392128886783249,
+      "learning_rate": 1.99450852192107e-05,
+      "loss": 0.7082,
+      "step": 355
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.23159963577625967,
+      "learning_rate": 1.9938191237648924e-05,
+      "loss": 0.7031,
+      "step": 360
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2522691194103305,
+      "learning_rate": 1.9930891060396757e-05,
+      "loss": 0.7094,
+      "step": 365
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2708112490882325,
+      "learning_rate": 1.992318498582846e-05,
+      "loss": 0.7201,
+      "step": 370
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.2293891910969228,
+      "learning_rate": 1.9915073328908217e-05,
+      "loss": 0.7144,
+      "step": 375
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.25206778778834,
+      "learning_rate": 1.9906556421177256e-05,
+      "loss": 0.7234,
+      "step": 380
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2518785514497742,
+      "learning_rate": 1.989763461074029e-05,
+      "loss": 0.7141,
+      "step": 385
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2378420502334953,
+      "learning_rate": 1.9888308262251286e-05,
+      "loss": 0.7231,
+      "step": 390
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.24009865726485224,
+      "learning_rate": 1.987857775689859e-05,
+      "loss": 0.7187,
+      "step": 395
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.28274675300361035,
+      "learning_rate": 1.9868443492389307e-05,
+      "loss": 0.7044,
+      "step": 400
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.22963475241854425,
+      "learning_rate": 1.985790588293308e-05,
+      "loss": 0.7104,
+      "step": 405
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.2377445508195736,
+      "learning_rate": 1.9846965359225127e-05,
+      "loss": 0.6946,
+      "step": 410
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2608944217378828,
+      "learning_rate": 1.9835622368428673e-05,
+      "loss": 0.7113,
+      "step": 415
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.24157694006779415,
+      "learning_rate": 1.9823877374156647e-05,
+      "loss": 0.698,
+      "step": 420
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.23398315907950198,
+      "learning_rate": 1.9811730856452754e-05,
+      "loss": 0.7257,
+      "step": 425
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.23894709403347192,
+      "learning_rate": 1.9799183311771823e-05,
+      "loss": 0.7184,
+      "step": 430
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.23431405547670192,
+      "learning_rate": 1.9786235252959555e-05,
+      "loss": 0.7128,
+      "step": 435
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2376569203749501,
+      "learning_rate": 1.977288720923153e-05,
+      "loss": 0.7203,
+      "step": 440
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.23231143839603255,
+      "learning_rate": 1.9759139726151597e-05,
+      "loss": 0.7082,
+      "step": 445
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.22602078925455668,
+      "learning_rate": 1.9744993365609563e-05,
+      "loss": 0.6944,
+      "step": 450
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.22861362046539935,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.698,
+      "step": 455
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.24188463913379904,
+      "learning_rate": 1.9715506341189795e-05,
+      "loss": 0.7015,
+      "step": 460
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2327706520398592,
+      "learning_rate": 1.970016688251147e-05,
+      "loss": 0.7054,
+      "step": 465
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2298533583392459,
+      "learning_rate": 1.9684430956720613e-05,
+      "loss": 0.7005,
+      "step": 470
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.23290007131084822,
+      "learning_rate": 1.966829920697905e-05,
+      "loss": 0.7098,
+      "step": 475
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.23281363580583736,
+      "learning_rate": 1.9651772292626804e-05,
+      "loss": 0.6818,
+      "step": 480
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.23817560008326671,
+      "learning_rate": 1.963485088915514e-05,
+      "loss": 0.7088,
+      "step": 485
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2350735880544215,
+      "learning_rate": 1.961753568817896e-05,
+      "loss": 0.7066,
+      "step": 490
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.23884064719455786,
+      "learning_rate": 1.959982739740854e-05,
+      "loss": 0.7042,
+      "step": 495
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.21790596438572063,
+      "learning_rate": 1.9581726740620585e-05,
+      "loss": 0.6757,
+      "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.23917884378106077,
+      "learning_rate": 1.9563234457628678e-05,
+      "loss": 0.6921,
+      "step": 505
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2399642009348881,
+      "learning_rate": 1.954435130425301e-05,
+      "loss": 0.7047,
+      "step": 510
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.23880300515157055,
+      "learning_rate": 1.952507805228951e-05,
+      "loss": 0.6884,
+      "step": 515
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.23179275898540247,
+      "learning_rate": 1.9505415489478293e-05,
+      "loss": 0.6932,
+      "step": 520
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2216104142333809,
+      "learning_rate": 1.9485364419471454e-05,
+      "loss": 0.6728,
+      "step": 525
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.22858244743422157,
+      "learning_rate": 1.9464925661800247e-05,
+      "loss": 0.6809,
+      "step": 530
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.22424934505435848,
+      "learning_rate": 1.9444100051841556e-05,
+      "loss": 0.6967,
+      "step": 535
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2895129667800956,
+      "learning_rate": 1.9422888440783773e-05,
+      "loss": 0.6989,
+      "step": 540
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.240457298966355,
+      "learning_rate": 1.9401291695592e-05,
+      "loss": 0.6818,
+      "step": 545
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.22825665925272676,
+      "learning_rate": 1.9379310698972618e-05,
+      "loss": 0.6922,
+      "step": 550
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2172530625853638,
+      "learning_rate": 1.935694634933721e-05,
+      "loss": 0.6627,
+      "step": 555
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.22221082939742373,
+      "learning_rate": 1.933419956076584e-05,
+      "loss": 0.6744,
+      "step": 560
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2264067795562855,
+      "learning_rate": 1.9311071262969675e-05,
+      "loss": 0.6641,
+      "step": 565
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2254067456859091,
+      "learning_rate": 1.9287562401253023e-05,
+      "loss": 0.6892,
+      "step": 570
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2370414298818578,
+      "learning_rate": 1.9263673936474662e-05,
+      "loss": 0.6779,
+      "step": 575
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.22087990811265876,
+      "learning_rate": 1.9239406845008583e-05,
+      "loss": 0.6805,
+      "step": 580
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.22405579155571978,
+      "learning_rate": 1.921476211870408e-05,
+      "loss": 0.6661,
+      "step": 585
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.22938270799667376,
+      "learning_rate": 1.918974076484521e-05,
+      "loss": 0.6773,
+      "step": 590
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.24245138817040104,
+      "learning_rate": 1.916434380610963e-05,
+      "loss": 0.6922,
+      "step": 595
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.22591029702471543,
+      "learning_rate": 1.9138572280526795e-05,
+      "loss": 0.6672,
+      "step": 600
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.22886503680106302,
+      "learning_rate": 1.911242724143552e-05,
+      "loss": 0.6574,
+      "step": 605
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.23592282593270214,
+      "learning_rate": 1.908590975744094e-05,
+      "loss": 0.6701,
+      "step": 610
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2263018036424681,
+      "learning_rate": 1.9059020912370836e-05,
+      "loss": 0.6645,
+      "step": 615
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.23573388350757823,
+      "learning_rate": 1.9031761805231322e-05,
+      "loss": 0.6789,
+      "step": 620
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2264306405740615,
+      "learning_rate": 1.9004133550161953e-05,
+      "loss": 0.6798,
+      "step": 625
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.23127140958344955,
+      "learning_rate": 1.8976137276390145e-05,
+      "loss": 0.6918,
+      "step": 630
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.22485640726090023,
+      "learning_rate": 1.894777412818506e-05,
+      "loss": 0.6579,
+      "step": 635
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2164772947483346,
+      "learning_rate": 1.891904526481083e-05,
+      "loss": 0.6729,
+      "step": 640
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.21930341038212908,
+      "learning_rate": 1.8889951860479165e-05,
+      "loss": 0.6636,
+      "step": 645
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.2212836429863629,
+      "learning_rate": 1.8860495104301346e-05,
+      "loss": 0.7046,
+      "step": 650
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.236222638103693,
+      "learning_rate": 1.8830676200239666e-05,
+      "loss": 0.6544,
+      "step": 655
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.23689174767504043,
+      "learning_rate": 1.8800496367058187e-05,
+      "loss": 0.6619,
+      "step": 660
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.22794708045955256,
+      "learning_rate": 1.8769956838272937e-05,
+      "loss": 0.6536,
+      "step": 665
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.2284737343207547,
+      "learning_rate": 1.8739058862101487e-05,
+      "loss": 0.6716,
+      "step": 670
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.22074952318779162,
+      "learning_rate": 1.8707803701411946e-05,
+      "loss": 0.671,
+      "step": 675
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2215061880912214,
+      "learning_rate": 1.8676192633671342e-05,
+      "loss": 0.6865,
+      "step": 680
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.23413437096611026,
+      "learning_rate": 1.8644226950893394e-05,
+      "loss": 0.6707,
+      "step": 685
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.22955684806244817,
+      "learning_rate": 1.861190795958573e-05,
+      "loss": 0.6835,
+      "step": 690
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.22476186793320183,
+      "learning_rate": 1.857923698069646e-05,
+      "loss": 0.6597,
+      "step": 695
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.22821748154651522,
+      "learning_rate": 1.8546215349560204e-05,
+      "loss": 0.6769,
+      "step": 700
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.22293250318189695,
+      "learning_rate": 1.8512844415843514e-05,
+      "loss": 0.6828,
+      "step": 705
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.22191425457543576,
+      "learning_rate": 1.8479125543489694e-05,
+      "loss": 0.6849,
+      "step": 710
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.22106154189199517,
+      "learning_rate": 1.844506011066308e-05,
+      "loss": 0.6877,
+      "step": 715
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.22662154758390868,
+      "learning_rate": 1.841064950969268e-05,
+      "loss": 0.6579,
+      "step": 720
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.22395783462295688,
+      "learning_rate": 1.8375895147015285e-05,
+      "loss": 0.6808,
+      "step": 725
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.22270568666818555,
+      "learning_rate": 1.8340798443117992e-05,
+      "loss": 0.6705,
+      "step": 730
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.2150504585631758,
+      "learning_rate": 1.8305360832480118e-05,
+      "loss": 0.6628,
+      "step": 735
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.21416406499964488,
+      "learning_rate": 1.8269583763514603e-05,
+      "loss": 0.6602,
+      "step": 740
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.22446619283908673,
+      "learning_rate": 1.8233468698508786e-05,
+      "loss": 0.6516,
+      "step": 745
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.22209820477583542,
+      "learning_rate": 1.819701711356464e-05,
+      "loss": 0.6719,
+      "step": 750
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.20930564484300637,
+      "learning_rate": 1.8160230498538464e-05,
+      "loss": 0.6462,
+      "step": 755
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2157300926603618,
+      "learning_rate": 1.8123110356979955e-05,
+      "loss": 0.6386,
+      "step": 760
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2278341187144425,
+      "learning_rate": 1.808565820607078e-05,
+      "loss": 0.6864,
+      "step": 765
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.22190749729143514,
+      "learning_rate": 1.8047875576562556e-05,
+      "loss": 0.6606,
+      "step": 770
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.22188524148964123,
+      "learning_rate": 1.8009764012714283e-05,
+      "loss": 0.6369,
+      "step": 775
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.24010299878120459,
+      "learning_rate": 1.7971325072229227e-05,
+      "loss": 0.6586,
+      "step": 780
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2129875521525412,
+      "learning_rate": 1.7932560326191265e-05,
+      "loss": 0.6446,
+      "step": 785
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.2284930031799763,
+      "learning_rate": 1.789347135900066e-05,
+      "loss": 0.6704,
+      "step": 790
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.21164688299648138,
+      "learning_rate": 1.7854059768309292e-05,
+      "loss": 0.6501,
+      "step": 795
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2185026582076693,
+      "learning_rate": 1.7814327164955388e-05,
+      "loss": 0.6504,
+      "step": 800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.23885266134914798,
+      "learning_rate": 1.777427517289766e-05,
+      "loss": 0.6534,
+      "step": 805
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.24735644831293754,
+      "learning_rate": 1.773390542914894e-05,
+      "loss": 0.6593,
+      "step": 810
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.21801160079829443,
+      "learning_rate": 1.7693219583709266e-05,
+      "loss": 0.6538,
+      "step": 815
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.23033125474961877,
+      "learning_rate": 1.765221929949845e-05,
+      "loss": 0.6544,
+      "step": 820
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.21636906024225588,
+      "learning_rate": 1.7610906252288097e-05,
+      "loss": 0.6678,
+      "step": 825
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.22862735644017182,
+      "learning_rate": 1.7569282130633137e-05,
+      "loss": 0.6676,
+      "step": 830
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.22135157314088189,
+      "learning_rate": 1.752734863580278e-05,
+      "loss": 0.6463,
+      "step": 835
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.21472268874726408,
+      "learning_rate": 1.7485107481711014e-05,
+      "loss": 0.6525,
+      "step": 840
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.21461981313008696,
+      "learning_rate": 1.7442560394846518e-05,
+      "loss": 0.6484,
+      "step": 845
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.21774234081011679,
+      "learning_rate": 1.739970911420213e-05,
+      "loss": 0.651,
+      "step": 850
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.21598579831580747,
+      "learning_rate": 1.7356555391203745e-05,
+      "loss": 0.6785,
+      "step": 855
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.22611280288574187,
+      "learning_rate": 1.7313100989638745e-05,
+      "loss": 0.6579,
+      "step": 860
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2118379153642089,
+      "learning_rate": 1.7269347685583913e-05,
+      "loss": 0.658,
+      "step": 865
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2098318370691198,
+      "learning_rate": 1.7225297267332815e-05,
+      "loss": 0.6628,
+      "step": 870
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2096338281124951,
+      "learning_rate": 1.7180951535322742e-05,
+      "loss": 0.6519,
+      "step": 875
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2277800903608631,
+      "learning_rate": 1.7136312302061097e-05,
+      "loss": 0.6396,
+      "step": 880
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2104470768411409,
+      "learning_rate": 1.7091381392051333e-05,
+      "loss": 0.6434,
+      "step": 885
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2142332846578606,
+      "learning_rate": 1.704616064171836e-05,
+      "loss": 0.6384,
+      "step": 890
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.21219425658206706,
+      "learning_rate": 1.7000651899333512e-05,
+      "loss": 0.6346,
+      "step": 895
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2208443696000645,
+      "learning_rate": 1.6954857024938976e-05,
+      "loss": 0.648,
+      "step": 900
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.21055402887891725,
+      "learning_rate": 1.6908777890271794e-05,
+      "loss": 0.6472,
+      "step": 905
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2122526858833542,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.6422,
+      "step": 910
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6909855604171753,
+      "eval_runtime": 13.3743,
+      "eval_samples_per_second": 103.034,
+      "eval_steps_per_second": 0.822,
+      "step": 910
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.2376946716415055,
+      "learning_rate": 1.6815774385082355e-05,
+      "loss": 0.6025,
+      "step": 915
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.21981152940016552,
+      "learning_rate": 1.6768853815817506e-05,
+      "loss": 0.6149,
+      "step": 920
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.2114064615721331,
+      "learning_rate": 1.6721656588639444e-05,
+      "loss": 0.6084,
+      "step": 925
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.21343882616611637,
+      "learning_rate": 1.6674184632602447e-05,
+      "loss": 0.6192,
+      "step": 930
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.20964848533593644,
+      "learning_rate": 1.6626439887989552e-05,
+      "loss": 0.577,
+      "step": 935
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.21080943869356272,
+      "learning_rate": 1.6578424306233282e-05,
+      "loss": 0.5858,
+      "step": 940
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.21972421289491473,
+      "learning_rate": 1.653013984983585e-05,
+      "loss": 0.5907,
+      "step": 945
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.2148077134860289,
+      "learning_rate": 1.6481588492288985e-05,
+      "loss": 0.5974,
+      "step": 950
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.222495841900069,
+      "learning_rate": 1.643277221799323e-05,
+      "loss": 0.5979,
+      "step": 955
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.21883932168474696,
+      "learning_rate": 1.638369302217687e-05,
+      "loss": 0.6077,
+      "step": 960
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.20756222937087987,
+      "learning_rate": 1.633435291081437e-05,
+      "loss": 0.5886,
+      "step": 965
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.22034735404299097,
+      "learning_rate": 1.6284753900544384e-05,
+      "loss": 0.6023,
+      "step": 970
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.2178991358059654,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.6077,
+      "step": 975
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.21185656324247812,
+      "learning_rate": 1.618478730266255e-05,
+      "loss": 0.5891,
+      "step": 980
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.2225195916998371,
+      "learning_rate": 1.6134423800904985e-05,
+      "loss": 0.6082,
+      "step": 985
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.21175099229044173,
+      "learning_rate": 1.6083809571781498e-05,
+      "loss": 0.6022,
+      "step": 990
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.21693130048041695,
+      "learning_rate": 1.6032946684006745e-05,
+      "loss": 0.5877,
+      "step": 995
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.20628677851436183,
+      "learning_rate": 1.598183721645858e-05,
+      "loss": 0.6025,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.21136866931809867,
+      "learning_rate": 1.5930483258093144e-05,
+      "loss": 0.6056,
+      "step": 1005
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.21628647967275302,
+      "learning_rate": 1.5878886907859423e-05,
+      "loss": 0.5973,
+      "step": 1010
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.21460811563007248,
+      "learning_rate": 1.5827050274613512e-05,
+      "loss": 0.6151,
+      "step": 1015
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.21019968808729894,
+      "learning_rate": 1.57749754770324e-05,
+      "loss": 0.5871,
+      "step": 1020
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.21602614964752764,
+      "learning_rate": 1.5722664643527362e-05,
+      "loss": 0.6088,
+      "step": 1025
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.21863820245310453,
+      "learning_rate": 1.567011991215699e-05,
+      "loss": 0.5968,
+      "step": 1030
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.21638329517362545,
+      "learning_rate": 1.561734343053979e-05,
+      "loss": 0.5879,
+      "step": 1035
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.21082524836877004,
+      "learning_rate": 1.5564337355766412e-05,
+      "loss": 0.583,
+      "step": 1040
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.2055779159254746,
+      "learning_rate": 1.551110385431148e-05,
+      "loss": 0.5934,
+      "step": 1045
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.22359885758488707,
+      "learning_rate": 1.5457645101945046e-05,
+      "loss": 0.5824,
+      "step": 1050
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.2194479570684916,
+      "learning_rate": 1.540396328364367e-05,
+      "loss": 0.6125,
+      "step": 1055
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.21187983654193793,
+      "learning_rate": 1.5350060593501086e-05,
+      "loss": 0.6028,
+      "step": 1060
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.21206606898137628,
+      "learning_rate": 1.5295939234638566e-05,
+      "loss": 0.5934,
+      "step": 1065
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.20258591515345375,
+      "learning_rate": 1.5241601419114842e-05,
+      "loss": 0.5775,
+      "step": 1070
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.2136809123465599,
+      "learning_rate": 1.5187049367835709e-05,
+      "loss": 0.5941,
+      "step": 1075
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.21728230317859182,
+      "learning_rate": 1.5132285310463243e-05,
+      "loss": 0.5832,
+      "step": 1080
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.2173442514170428,
+      "learning_rate": 1.507731148532468e-05,
+      "loss": 0.5896,
+      "step": 1085
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.2171859843513773,
+      "learning_rate": 1.5022130139320916e-05,
+      "loss": 0.6007,
+      "step": 1090
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.22340196606689453,
+      "learning_rate": 1.4966743527834691e-05,
+      "loss": 0.6034,
+      "step": 1095
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.20721993882081483,
+      "learning_rate": 1.4911153914638388e-05,
+      "loss": 0.6027,
+      "step": 1100
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.21607496950020452,
+      "learning_rate": 1.4855363571801523e-05,
+      "loss": 0.6128,
+      "step": 1105
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.21215405353798844,
+      "learning_rate": 1.4799374779597866e-05,
+      "loss": 0.583,
+      "step": 1110
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.21724719376448562,
+      "learning_rate": 1.474318982641225e-05,
+      "loss": 0.5913,
+      "step": 1115
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.22458471606601424,
+      "learning_rate": 1.4686811008647037e-05,
+      "loss": 0.612,
+      "step": 1120
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.21247586240459654,
+      "learning_rate": 1.463024063062827e-05,
+      "loss": 0.5855,
+      "step": 1125
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.22045045025828708,
+      "learning_rate": 1.457348100451146e-05,
+      "loss": 0.5883,
+      "step": 1130
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.214769725773024,
+      "learning_rate": 1.4516534450187126e-05,
+      "loss": 0.5877,
+      "step": 1135
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.2160947649465179,
+      "learning_rate": 1.4459403295185933e-05,
+      "loss": 0.5951,
+      "step": 1140
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.21080831461558835,
+      "learning_rate": 1.4402089874583594e-05,
+      "loss": 0.5616,
+      "step": 1145
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.3517838242091068,
+      "learning_rate": 1.4344596530905412e-05,
+      "loss": 0.5981,
+      "step": 1150
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.2170223068256742,
+      "learning_rate": 1.4286925614030542e-05,
+      "loss": 0.5962,
+      "step": 1155
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.20876572174386707,
+      "learning_rate": 1.4229079481095949e-05,
+      "loss": 0.5705,
+      "step": 1160
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.2114530881165322,
+      "learning_rate": 1.4171060496400055e-05,
+      "loss": 0.5831,
+      "step": 1165
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.2124316227899679,
+      "learning_rate": 1.4112871031306118e-05,
+      "loss": 0.5927,
+      "step": 1170
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.24069796832607096,
+      "learning_rate": 1.4054513464145303e-05,
+      "loss": 0.5843,
+      "step": 1175
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.21761542079259927,
+      "learning_rate": 1.3995990180119478e-05,
+      "loss": 0.5913,
+      "step": 1180
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.22376197027518,
+      "learning_rate": 1.3937303571203718e-05,
+      "loss": 0.5937,
+      "step": 1185
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.21270100949939988,
+      "learning_rate": 1.387845603604855e-05,
+      "loss": 0.6087,
+      "step": 1190
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.2061356457768136,
+      "learning_rate": 1.3819449979881907e-05,
+      "loss": 0.5913,
+      "step": 1195
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.21386723380022615,
+      "learning_rate": 1.3760287814410822e-05,
+      "loss": 0.5993,
+      "step": 1200
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.21228068552627186,
+      "learning_rate": 1.3700971957722861e-05,
+      "loss": 0.5957,
+      "step": 1205
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.22337829074807855,
+      "learning_rate": 1.3641504834187288e-05,
+      "loss": 0.5877,
+      "step": 1210
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.20603083898424746,
+      "learning_rate": 1.3581888874355969e-05,
+      "loss": 0.5925,
+      "step": 1215
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.21192778054346198,
+      "learning_rate": 1.3522126514864047e-05,
+      "loss": 0.5891,
+      "step": 1220
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.2084884476447279,
+      "learning_rate": 1.346222019833033e-05,
+      "loss": 0.5834,
+      "step": 1225
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.2147834275155995,
+      "learning_rate": 1.3402172373257466e-05,
+      "loss": 0.5699,
+      "step": 1230
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.2098959357243527,
+      "learning_rate": 1.3341985493931877e-05,
+      "loss": 0.5962,
+      "step": 1235
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.21524463993944057,
+      "learning_rate": 1.3281662020323434e-05,
+      "loss": 0.5732,
+      "step": 1240
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.21867167573117696,
+      "learning_rate": 1.3221204417984907e-05,
+      "loss": 0.5955,
+      "step": 1245
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.21413713721132682,
+      "learning_rate": 1.3160615157951218e-05,
+      "loss": 0.6075,
+      "step": 1250
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.21839276156580137,
+      "learning_rate": 1.3099896716638414e-05,
+      "loss": 0.6037,
+      "step": 1255
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.2083037589975683,
+      "learning_rate": 1.303905157574247e-05,
+      "loss": 0.5824,
+      "step": 1260
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.2113647393844558,
+      "learning_rate": 1.297808222213785e-05,
+      "loss": 0.583,
+      "step": 1265
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.21208258707761682,
+      "learning_rate": 1.2916991147775867e-05,
+      "loss": 0.5968,
+      "step": 1270
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.21585097977939674,
+      "learning_rate": 1.2855780849582828e-05,
+      "loss": 0.605,
+      "step": 1275
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.2177190382165568,
+      "learning_rate": 1.2794453829357974e-05,
+      "loss": 0.5917,
+      "step": 1280
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.20918133994979798,
+      "learning_rate": 1.2733012593671235e-05,
+      "loss": 0.5808,
+      "step": 1285
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.20727620915430647,
+      "learning_rate": 1.2671459653760781e-05,
+      "loss": 0.5848,
+      "step": 1290
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.21127807703832494,
+      "learning_rate": 1.2609797525430374e-05,
+      "loss": 0.5918,
+      "step": 1295
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.22995739968919704,
+      "learning_rate": 1.2548028728946548e-05,
+      "loss": 0.5788,
+      "step": 1300
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.283656419786389,
+      "learning_rate": 1.2486155788935599e-05,
+      "loss": 0.5696,
+      "step": 1305
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.2060037733197605,
+      "learning_rate": 1.24241812342804e-05,
+      "loss": 0.5679,
+      "step": 1310
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.20635796088681332,
+      "learning_rate": 1.2362107598017037e-05,
+      "loss": 0.5724,
+      "step": 1315
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.22467393881977182,
+      "learning_rate": 1.2299937417231269e-05,
+      "loss": 0.5955,
+      "step": 1320
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.2074247154565041,
+      "learning_rate": 1.2237673232954854e-05,
+      "loss": 0.5971,
+      "step": 1325
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.2424465336794506,
+      "learning_rate": 1.2175317590061676e-05,
+      "loss": 0.5781,
+      "step": 1330
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.22257500583547102,
+      "learning_rate": 1.2112873037163728e-05,
+      "loss": 0.5839,
+      "step": 1335
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.2066344256103609,
+      "learning_rate": 1.2050342126506958e-05,
+      "loss": 0.5739,
+      "step": 1340
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.22883829030621783,
+      "learning_rate": 1.1987727413866936e-05,
+      "loss": 0.5834,
+      "step": 1345
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.2078381748570218,
+      "learning_rate": 1.1925031458444416e-05,
+      "loss": 0.5987,
+      "step": 1350
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.19775167797301507,
+      "learning_rate": 1.1862256822760704e-05,
+      "loss": 0.6014,
+      "step": 1355
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.22122261973414395,
+      "learning_rate": 1.1799406072552963e-05,
+      "loss": 0.6051,
+      "step": 1360
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.2048271696065503,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.5836,
+      "step": 1365
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.2089570875625985,
+      "learning_rate": 1.1673486506963824e-05,
+      "loss": 0.5969,
+      "step": 1370
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.20686459307988367,
+      "learning_rate": 1.1610422838191473e-05,
+      "loss": 0.5838,
+      "step": 1375
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.2011184871623206,
+      "learning_rate": 1.1547293347902813e-05,
+      "loss": 0.5809,
+      "step": 1380
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.20796307453083696,
+      "learning_rate": 1.148410061633869e-05,
+      "loss": 0.577,
+      "step": 1385
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.21285626663848575,
+      "learning_rate": 1.1420847226324746e-05,
+      "loss": 0.5842,
+      "step": 1390
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.21073449630208443,
+      "learning_rate": 1.135753576316588e-05,
+      "loss": 0.5631,
+      "step": 1395
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.21419628737948346,
+      "learning_rate": 1.1294168814540554e-05,
+      "loss": 0.5725,
+      "step": 1400
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.21145643817601928,
+      "learning_rate": 1.1230748970395056e-05,
+      "loss": 0.5841,
+      "step": 1405
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.21985931289420635,
+      "learning_rate": 1.1167278822837621e-05,
+      "loss": 0.5921,
+      "step": 1410
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.21769355752757327,
+      "learning_rate": 1.1103760966032497e-05,
+      "loss": 0.5969,
+      "step": 1415
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.205702651788512,
+      "learning_rate": 1.1040197996093915e-05,
+      "loss": 0.5998,
+      "step": 1420
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.2123850240700951,
+      "learning_rate": 1.0976592510979982e-05,
+      "loss": 0.602,
+      "step": 1425
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.2080343816532754,
+      "learning_rate": 1.0912947110386484e-05,
+      "loss": 0.5779,
+      "step": 1430
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.24850849809790562,
+      "learning_rate": 1.084926439564065e-05,
+      "loss": 0.6032,
+      "step": 1435
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.21564897773144823,
+      "learning_rate": 1.0785546969594813e-05,
+      "loss": 0.5869,
+      "step": 1440
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.20762144286700152,
+      "learning_rate": 1.0721797436520044e-05,
+      "loss": 0.5826,
+      "step": 1445
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.2063081386274062,
+      "learning_rate": 1.0658018401999681e-05,
+      "loss": 0.5704,
+      "step": 1450
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.20663776641786638,
+      "learning_rate": 1.0594212472822865e-05,
+      "loss": 0.5699,
+      "step": 1455
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2041445625688445,
+      "learning_rate": 1.053038225687798e-05,
+      "loss": 0.5844,
+      "step": 1460
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.2130137089909296,
+      "learning_rate": 1.0466530363046057e-05,
+      "loss": 0.5863,
+      "step": 1465
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.20861757470403922,
+      "learning_rate": 1.0402659401094154e-05,
+      "loss": 0.5967,
+      "step": 1470
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.2027441783860282,
+      "learning_rate": 1.033877198156868e-05,
+      "loss": 0.5897,
+      "step": 1475
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.213846779001926,
+      "learning_rate": 1.0274870715688713e-05,
+      "loss": 0.6025,
+      "step": 1480
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.2127779802918096,
+      "learning_rate": 1.0210958215239249e-05,
+      "loss": 0.6056,
+      "step": 1485
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.20745193969187556,
+      "learning_rate": 1.0147037092464469e-05,
+      "loss": 0.577,
+      "step": 1490
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.21182819095935948,
+      "learning_rate": 1.0083109959960974e-05,
+      "loss": 0.5864,
+      "step": 1495
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.19696271189726422,
+      "learning_rate": 1.0019179430570984e-05,
+      "loss": 0.5928,
+      "step": 1500
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.20879291422466129,
+      "learning_rate": 9.955248117275566e-06,
+      "loss": 0.5759,
+      "step": 1505
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.20354233979841574,
+      "learning_rate": 9.891318633087831e-06,
+      "loss": 0.5752,
+      "step": 1510
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.20873959818273613,
+      "learning_rate": 9.827393590946116e-06,
+      "loss": 0.5781,
+      "step": 1515
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.20270163619729287,
+      "learning_rate": 9.763475603607215e-06,
+      "loss": 0.5766,
+      "step": 1520
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.20654005706496942,
+      "learning_rate": 9.699567283539567e-06,
+      "loss": 0.5681,
+      "step": 1525
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.20618557107103305,
+      "learning_rate": 9.635671242816503e-06,
+      "loss": 0.609,
+      "step": 1530
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.21061722996416557,
+      "learning_rate": 9.571790093009445e-06,
+      "loss": 0.5934,
+      "step": 1535
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.21093457717343486,
+      "learning_rate": 9.50792644508122e-06,
+      "loss": 0.581,
+      "step": 1540
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.21238370099560738,
+      "learning_rate": 9.44408290927929e-06,
+      "loss": 0.5739,
+      "step": 1545
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.2164905762404212,
+      "learning_rate": 9.380262095029113e-06,
+      "loss": 0.5927,
+      "step": 1550
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.20454952313454147,
+      "learning_rate": 9.316466610827446e-06,
+      "loss": 0.5873,
+      "step": 1555
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.20592385724986123,
+      "learning_rate": 9.252699064135759e-06,
+      "loss": 0.5671,
+      "step": 1560
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.2033785032533706,
+      "learning_rate": 9.188962061273664e-06,
+      "loss": 0.5658,
+      "step": 1565
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.21054461531122468,
+      "learning_rate": 9.125258207312365e-06,
+      "loss": 0.5792,
+      "step": 1570
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.21120511900125027,
+      "learning_rate": 9.061590105968208e-06,
+      "loss": 0.5854,
+      "step": 1575
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.20830877482379653,
+      "learning_rate": 8.997960359496248e-06,
+      "loss": 0.5826,
+      "step": 1580
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.20288306787814717,
+      "learning_rate": 8.934371568583893e-06,
+      "loss": 0.5706,
+      "step": 1585
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21694924382055683,
+      "learning_rate": 8.8708263322446e-06,
+      "loss": 0.5951,
+      "step": 1590
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.20903099761718094,
+      "learning_rate": 8.807327247711667e-06,
+      "loss": 0.5824,
+      "step": 1595
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.20063759680689586,
+      "learning_rate": 8.743876910332057e-06,
+      "loss": 0.5614,
+      "step": 1600
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.20409842230229638,
+      "learning_rate": 8.680477913460339e-06,
+      "loss": 0.5946,
+      "step": 1605
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.20466612084153943,
+      "learning_rate": 8.617132848352672e-06,
+      "loss": 0.5652,
+      "step": 1610
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.20697633678427196,
+      "learning_rate": 8.553844304060908e-06,
+      "loss": 0.5812,
+      "step": 1615
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.21720588749316946,
+      "learning_rate": 8.490614867326775e-06,
+      "loss": 0.6117,
+      "step": 1620
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.20226043800686028,
+      "learning_rate": 8.427447122476148e-06,
+      "loss": 0.5813,
+      "step": 1625
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.20240033305212438,
+      "learning_rate": 8.364343651313406e-06,
+      "loss": 0.5838,
+      "step": 1630
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.20457722466303066,
+      "learning_rate": 8.301307033015928e-06,
+      "loss": 0.5838,
+      "step": 1635
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.21113002739789974,
+      "learning_rate": 8.23833984402868e-06,
+      "loss": 0.5642,
+      "step": 1640
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.20884646327430137,
+      "learning_rate": 8.175444657958875e-06,
+      "loss": 0.5887,
+      "step": 1645
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.2117374486270568,
+      "learning_rate": 8.112624045470834e-06,
+      "loss": 0.5586,
+      "step": 1650
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.2153924095751537,
+      "learning_rate": 8.04988057418088e-06,
+      "loss": 0.5586,
+      "step": 1655
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.2242880757841404,
+      "learning_rate": 7.987216808552409e-06,
+      "loss": 0.584,
+      "step": 1660
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.2052097826707033,
+      "learning_rate": 7.924635309791065e-06,
+      "loss": 0.5734,
+      "step": 1665
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.20970207818516165,
+      "learning_rate": 7.862138635740078e-06,
+      "loss": 0.5794,
+      "step": 1670
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.22854744935308324,
+      "learning_rate": 7.799729340775688e-06,
+      "loss": 0.5665,
+      "step": 1675
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.21044359070616686,
+      "learning_rate": 7.73740997570278e-06,
+      "loss": 0.5798,
+      "step": 1680
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.22708073388787278,
+      "learning_rate": 7.675183087650592e-06,
+      "loss": 0.5801,
+      "step": 1685
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.2033282205763091,
+      "learning_rate": 7.613051219968624e-06,
+      "loss": 0.5839,
+      "step": 1690
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.20524876955037163,
+      "learning_rate": 7.551016912122692e-06,
+      "loss": 0.5669,
+      "step": 1695
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.2084171272109649,
+      "learning_rate": 7.489082699591128e-06,
+      "loss": 0.5772,
+      "step": 1700
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.2045659246543415,
+      "learning_rate": 7.4272511137611405e-06,
+      "loss": 0.5888,
+      "step": 1705
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.2238357346707814,
+      "learning_rate": 7.3655246818253626e-06,
+      "loss": 0.5778,
+      "step": 1710
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.20675904524387453,
+      "learning_rate": 7.303905926678565e-06,
+      "loss": 0.5716,
+      "step": 1715
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.19722673110072383,
+      "learning_rate": 7.242397366814516e-06,
+      "loss": 0.5807,
+      "step": 1720
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.2048782845337188,
+      "learning_rate": 7.181001516223074e-06,
+      "loss": 0.5826,
+      "step": 1725
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.20915644349360044,
+      "learning_rate": 7.1197208842874175e-06,
+      "loss": 0.5604,
+      "step": 1730
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.20273160113226266,
+      "learning_rate": 7.058557975681488e-06,
+      "loss": 0.5333,
+      "step": 1735
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.20926689973709214,
+      "learning_rate": 6.997515290267611e-06,
+      "loss": 0.5946,
+      "step": 1740
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.21243148030222134,
+      "learning_rate": 6.936595322994328e-06,
+      "loss": 0.5704,
+      "step": 1745
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.2322671841870559,
+      "learning_rate": 6.8758005637944245e-06,
+      "loss": 0.5672,
+      "step": 1750
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.20191574871457757,
+      "learning_rate": 6.815133497483157e-06,
+      "loss": 0.5531,
+      "step": 1755
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.1979263709848421,
+      "learning_rate": 6.754596603656687e-06,
+      "loss": 0.5855,
+      "step": 1760
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.20297785849664604,
+      "learning_rate": 6.694192356590743e-06,
+      "loss": 0.5611,
+      "step": 1765
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.2057255315804723,
+      "learning_rate": 6.633923225139498e-06,
+      "loss": 0.5603,
+      "step": 1770
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.2039103225151876,
+      "learning_rate": 6.573791672634638e-06,
+      "loss": 0.564,
+      "step": 1775
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.20729859585281207,
+      "learning_rate": 6.513800156784709e-06,
+      "loss": 0.5665,
+      "step": 1780
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.21039586635611288,
+      "learning_rate": 6.453951129574644e-06,
+      "loss": 0.5731,
+      "step": 1785
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.2517268650469455,
+      "learning_rate": 6.394247037165559e-06,
+      "loss": 0.5895,
+      "step": 1790
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.20420292346101634,
+      "learning_rate": 6.3346903197947564e-06,
+      "loss": 0.5822,
+      "step": 1795
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.2005713051020868,
+      "learning_rate": 6.275283411676008e-06,
+      "loss": 0.5747,
+      "step": 1800
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.20383448396361142,
+      "learning_rate": 6.216028740900042e-06,
+      "loss": 0.564,
+      "step": 1805
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.20518916264594467,
+      "learning_rate": 6.1569287293353274e-06,
+      "loss": 0.569,
+      "step": 1810
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.20991517111604094,
+      "learning_rate": 6.097985792529055e-06,
+      "loss": 0.5776,
+      "step": 1815
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20901449217066023,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.5701,
+      "step": 1820
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6639273166656494,
+      "eval_runtime": 13.2474,
+      "eval_samples_per_second": 104.021,
+      "eval_steps_per_second": 0.83,
+      "step": 1820
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.22019281423746326,
+      "learning_rate": 5.980580773182214e-06,
+      "loss": 0.522,
+      "step": 1825
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.20628500931618077,
+      "learning_rate": 5.922123489242499e-06,
+      "loss": 0.5217,
+      "step": 1830
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.21214052920599313,
+      "learning_rate": 5.8638328770667905e-06,
+      "loss": 0.5158,
+      "step": 1835
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.2125306506706992,
+      "learning_rate": 5.805711319120358e-06,
+      "loss": 0.5266,
+      "step": 1840
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.20497451303661474,
+      "learning_rate": 5.747761190958859e-06,
+      "loss": 0.5379,
+      "step": 1845
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.20908534530239564,
+      "learning_rate": 5.689984861131221e-06,
+      "loss": 0.5235,
+      "step": 1850
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.21454631325571177,
+      "learning_rate": 5.632384691082874e-06,
+      "loss": 0.559,
+      "step": 1855
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.20512681342425096,
+      "learning_rate": 5.5749630350592e-06,
+      "loss": 0.5112,
+      "step": 1860
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.21863556347579605,
+      "learning_rate": 5.517722240009319e-06,
+      "loss": 0.5252,
+      "step": 1865
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.2042884660329648,
+      "learning_rate": 5.460664645490172e-06,
+      "loss": 0.5319,
+      "step": 1870
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.20585363297531442,
+      "learning_rate": 5.403792583570884e-06,
+      "loss": 0.5486,
+      "step": 1875
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.21017174229067934,
+      "learning_rate": 5.347108378737469e-06,
+      "loss": 0.5219,
+      "step": 1880
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.20323326084962492,
+      "learning_rate": 5.290614347797802e-06,
+      "loss": 0.5304,
+      "step": 1885
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.20641023175360712,
+      "learning_rate": 5.234312799786921e-06,
+      "loss": 0.5078,
+      "step": 1890
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.20699085777952853,
+      "learning_rate": 5.1782060358726885e-06,
+      "loss": 0.541,
+      "step": 1895
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.21849299793363283,
+      "learning_rate": 5.122296349261695e-06,
+      "loss": 0.5382,
+      "step": 1900
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.2225675454375723,
+      "learning_rate": 5.066586025105558e-06,
+      "loss": 0.5222,
+      "step": 1905
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.21820736824894094,
+      "learning_rate": 5.011077340407509e-06,
+      "loss": 0.521,
+      "step": 1910
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.21040780570604573,
+      "learning_rate": 4.955772563929334e-06,
+      "loss": 0.5138,
+      "step": 1915
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.20328121606226746,
+      "learning_rate": 4.900673956098644e-06,
+      "loss": 0.5,
+      "step": 1920
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.20307162400180162,
+      "learning_rate": 4.845783768916482e-06,
+      "loss": 0.5205,
+      "step": 1925
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.2145754172951753,
+      "learning_rate": 4.79110424586528e-06,
+      "loss": 0.5361,
+      "step": 1930
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.22278545561346286,
+      "learning_rate": 4.736637621817176e-06,
+      "loss": 0.5415,
+      "step": 1935
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.20777015428265447,
+      "learning_rate": 4.682386122942649e-06,
+      "loss": 0.5466,
+      "step": 1940
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.20476960423981388,
+      "learning_rate": 4.628351966619531e-06,
+      "loss": 0.5356,
+      "step": 1945
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.2026935858356193,
+      "learning_rate": 4.5745373613424075e-06,
+      "loss": 0.5183,
+      "step": 1950
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.20396283481465377,
+      "learning_rate": 4.520944506632314e-06,
+      "loss": 0.5282,
+      "step": 1955
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.20723703288940273,
+      "learning_rate": 4.467575592946865e-06,
+      "loss": 0.5353,
+      "step": 1960
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.20283509715409914,
+      "learning_rate": 4.414432801590703e-06,
+      "loss": 0.5253,
+      "step": 1965
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.2052800409715183,
+      "learning_rate": 4.361518304626366e-06,
+      "loss": 0.5144,
+      "step": 1970
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.19650849856593194,
+      "learning_rate": 4.308834264785483e-06,
+      "loss": 0.515,
+      "step": 1975
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.20863894389929338,
+      "learning_rate": 4.256382835380421e-06,
+      "loss": 0.5202,
+      "step": 1980
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.20698871916210282,
+      "learning_rate": 4.204166160216216e-06,
+      "loss": 0.5341,
+      "step": 1985
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.21288394644934694,
+      "learning_rate": 4.1521863735030065e-06,
+      "loss": 0.5428,
+      "step": 1990
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.21106167476818527,
+      "learning_rate": 4.100445599768774e-06,
+      "loss": 0.522,
+      "step": 1995
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.20964196528234977,
+      "learning_rate": 4.048945953772504e-06,
+      "loss": 0.5294,
+      "step": 2000
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.2186729758235947,
+      "learning_rate": 3.99768954041778e-06,
+      "loss": 0.5258,
+      "step": 2005
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.21074477316001103,
+      "learning_rate": 3.946678454666719e-06,
+      "loss": 0.5296,
+      "step": 2010
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.2082023730818782,
+      "learning_rate": 3.89591478145437e-06,
+      "loss": 0.5232,
+      "step": 2015
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.211665046662059,
+      "learning_rate": 3.845400595603482e-06,
+      "loss": 0.5325,
+      "step": 2020
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.20452212904152248,
+      "learning_rate": 3.79513796173971e-06,
+      "loss": 0.5208,
+      "step": 2025
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.20097361934014168,
+      "learning_rate": 3.745128934207225e-06,
+      "loss": 0.5154,
+      "step": 2030
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.20835101950643772,
+      "learning_rate": 3.695375556984764e-06,
+      "loss": 0.5221,
+      "step": 2035
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.20751752347710595,
+      "learning_rate": 3.6458798636020477e-06,
+      "loss": 0.5208,
+      "step": 2040
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.2083029476627408,
+      "learning_rate": 3.59664387705672e-06,
+      "loss": 0.524,
+      "step": 2045
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.20547050805474043,
+      "learning_rate": 3.5476696097316253e-06,
+      "loss": 0.5224,
+      "step": 2050
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.20721249112618484,
+      "learning_rate": 3.4989590633125583e-06,
+      "loss": 0.5335,
+      "step": 2055
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.2084694829774017,
+      "learning_rate": 3.450514228706482e-06,
+      "loss": 0.5229,
+      "step": 2060
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.20216282130770613,
+      "learning_rate": 3.4023370859601192e-06,
+      "loss": 0.5375,
+      "step": 2065
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.2036489936294621,
+      "learning_rate": 3.3544296041790457e-06,
+      "loss": 0.5123,
+      "step": 2070
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.20447914104651402,
+      "learning_rate": 3.3067937414471986e-06,
+      "loss": 0.5283,
+      "step": 2075
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.20966243005652113,
+      "learning_rate": 3.2594314447468457e-06,
+      "loss": 0.5207,
+      "step": 2080
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.20579910881393176,
+      "learning_rate": 3.2123446498790214e-06,
+      "loss": 0.518,
+      "step": 2085
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.19982035514392868,
+      "learning_rate": 3.1655352813843886e-06,
+      "loss": 0.53,
+      "step": 2090
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.2114271078042674,
+      "learning_rate": 3.1190052524645752e-06,
+      "loss": 0.5297,
+      "step": 2095
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.20832244818822046,
+      "learning_rate": 3.0727564649040066e-06,
+      "loss": 0.5102,
+      "step": 2100
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.2008612540571781,
+      "learning_rate": 3.0267908089921438e-06,
+      "loss": 0.525,
+      "step": 2105
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.21335420821701767,
+      "learning_rate": 2.9811101634462414e-06,
+      "loss": 0.5161,
+      "step": 2110
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.20450727458510107,
+      "learning_rate": 2.93571639533455e-06,
+      "loss": 0.5139,
+      "step": 2115
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.213686615068082,
+      "learning_rate": 2.8906113600000153e-06,
+      "loss": 0.5203,
+      "step": 2120
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.20772690016178588,
+      "learning_rate": 2.8457969009844354e-06,
+      "loss": 0.5437,
+      "step": 2125
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.20632381814936407,
+      "learning_rate": 2.8012748499531195e-06,
+      "loss": 0.5318,
+      "step": 2130
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.2016664102243559,
+      "learning_rate": 2.7570470266200177e-06,
+      "loss": 0.5165,
+      "step": 2135
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.20520163431623825,
+      "learning_rate": 2.713115238673356e-06,
+      "loss": 0.5193,
+      "step": 2140
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.214071163971577,
+      "learning_rate": 2.669481281701739e-06,
+      "loss": 0.5268,
+      "step": 2145
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.20652575043829738,
+      "learning_rate": 2.626146939120757e-06,
+      "loss": 0.5176,
+      "step": 2150
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.20623703636177199,
+      "learning_rate": 2.5831139821001184e-06,
+      "loss": 0.5194,
+      "step": 2155
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.2073488736443259,
+      "learning_rate": 2.5403841694912333e-06,
+      "loss": 0.521,
+      "step": 2160
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.20428316103740377,
+      "learning_rate": 2.497959247755335e-06,
+      "loss": 0.522,
+      "step": 2165
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.20624815834176138,
+      "learning_rate": 2.455840950892099e-06,
+      "loss": 0.5338,
+      "step": 2170
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.2107922125349263,
+      "learning_rate": 2.414031000368767e-06,
+      "loss": 0.5381,
+      "step": 2175
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.20453939515184638,
+      "learning_rate": 2.372531105049789e-06,
+      "loss": 0.5183,
+      "step": 2180
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.19793223071462618,
+      "learning_rate": 2.331342961126988e-06,
+      "loss": 0.5113,
+      "step": 2185
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.21378964248804647,
+      "learning_rate": 2.290468252050204e-06,
+      "loss": 0.5296,
+      "step": 2190
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.22063310823848487,
+      "learning_rate": 2.2499086484585255e-06,
+      "loss": 0.5169,
+      "step": 2195
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.20381232643959812,
+      "learning_rate": 2.2096658081119793e-06,
+      "loss": 0.5196,
+      "step": 2200
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.21044163878960068,
+      "learning_rate": 2.1697413758237785e-06,
+      "loss": 0.5373,
+      "step": 2205
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.20577762743347522,
+      "learning_rate": 2.130136983393112e-06,
+      "loss": 0.5095,
+      "step": 2210
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.20351905534806264,
+      "learning_rate": 2.0908542495384276e-06,
+      "loss": 0.5238,
+      "step": 2215
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.19865856316493957,
+      "learning_rate": 2.051894779831286e-06,
+      "loss": 0.516,
+      "step": 2220
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.19763372174700705,
+      "learning_rate": 2.0132601666307295e-06,
+      "loss": 0.5073,
+      "step": 2225
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.19981546411123563,
+      "learning_rate": 1.9749519890182035e-06,
+      "loss": 0.5233,
+      "step": 2230
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.2033638338024947,
+      "learning_rate": 1.936971812733012e-06,
+      "loss": 0.5023,
+      "step": 2235
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.20822189802082794,
+      "learning_rate": 1.8993211901083353e-06,
+      "loss": 0.5009,
+      "step": 2240
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.2079466895136193,
+      "learning_rate": 1.8620016600077516e-06,
+      "loss": 0.5256,
+      "step": 2245
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.20439899215227353,
+      "learning_rate": 1.8250147477623836e-06,
+      "loss": 0.5365,
+      "step": 2250
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.22075705014027322,
+      "learning_rate": 1.7883619651085194e-06,
+      "loss": 0.5168,
+      "step": 2255
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.1964170868119619,
+      "learning_rate": 1.7520448101258325e-06,
+      "loss": 0.5173,
+      "step": 2260
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.2018340951265649,
+      "learning_rate": 1.716064767176172e-06,
+      "loss": 0.5208,
+      "step": 2265
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.20205110525587222,
+      "learning_rate": 1.6804233068428678e-06,
+      "loss": 0.5321,
+      "step": 2270
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.21357970053476708,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.5203,
+      "step": 2275
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.2060738726003442,
+      "learning_rate": 1.6101619471060415e-06,
+      "loss": 0.5206,
+      "step": 2280
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.20422451049362417,
+      "learning_rate": 1.5755449194385164e-06,
+      "loss": 0.5183,
+      "step": 2285
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.2002944726641853,
+      "learning_rate": 1.5412722177419658e-06,
+      "loss": 0.5315,
+      "step": 2290
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.20080246126740545,
+      "learning_rate": 1.5073452428169444e-06,
+      "loss": 0.5302,
+      "step": 2295
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.20361752591083399,
+      "learning_rate": 1.4737653813333774e-06,
+      "loss": 0.5178,
+      "step": 2300
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.19999788848075653,
+      "learning_rate": 1.4405340057739203e-06,
+      "loss": 0.5192,
+      "step": 2305
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.1959282126715599,
+      "learning_rate": 1.407652474377832e-06,
+      "loss": 0.5156,
+      "step": 2310
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.20774381542552106,
+      "learning_rate": 1.3751221310854778e-06,
+      "loss": 0.5056,
+      "step": 2315
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.2038197815633597,
+      "learning_rate": 1.3429443054833913e-06,
+      "loss": 0.5265,
+      "step": 2320
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.20325668884167009,
+      "learning_rate": 1.311120312749935e-06,
+      "loss": 0.5234,
+      "step": 2325
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.20390134033380405,
+      "learning_rate": 1.2796514536015492e-06,
+      "loss": 0.5368,
+      "step": 2330
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.20166563167725796,
+      "learning_rate": 1.2485390142395793e-06,
+      "loss": 0.5205,
+      "step": 2335
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.2022982713597928,
+      "learning_rate": 1.2177842662977136e-06,
+      "loss": 0.5231,
+      "step": 2340
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.21218295817596197,
+      "learning_rate": 1.1873884667900125e-06,
+      "loss": 0.5439,
+      "step": 2345
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.20473864934409344,
+      "learning_rate": 1.1573528580595195e-06,
+      "loss": 0.521,
+      "step": 2350
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.20949092154655793,
+      "learning_rate": 1.1276786677274866e-06,
+      "loss": 0.5105,
+      "step": 2355
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.20094255278913592,
+      "learning_rate": 1.0983671086432146e-06,
+      "loss": 0.5128,
+      "step": 2360
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.2057662784043456,
+      "learning_rate": 1.069419378834461e-06,
+      "loss": 0.5385,
+      "step": 2365
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.20176044390537098,
+      "learning_rate": 1.040836661458482e-06,
+      "loss": 0.5171,
+      "step": 2370
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.21932275472178112,
+      "learning_rate": 1.0126201247536783e-06,
+      "loss": 0.528,
+      "step": 2375
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.19746784289323338,
+      "learning_rate": 9.8477092199184e-07,
+      "loss": 0.511,
+      "step": 2380
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.20034469208109756,
+      "learning_rate": 9.57290191431013e-07,
+      "loss": 0.5227,
+      "step": 2385
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.20104497306207902,
+      "learning_rate": 9.301790562689794e-07,
+      "loss": 0.5277,
+      "step": 2390
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.1972303787668993,
+      "learning_rate": 9.034386245973359e-07,
+      "loss": 0.5147,
+      "step": 2395
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.20641734055273483,
+      "learning_rate": 8.770699893562273e-07,
+      "loss": 0.5256,
+      "step": 2400
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.2083707616895028,
+      "learning_rate": 8.510742282896545e-07,
+      "loss": 0.5154,
+      "step": 2405
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.20003452385731113,
+      "learning_rate": 8.254524039014289e-07,
+      "loss": 0.5333,
+      "step": 2410
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.20109885864318555,
+      "learning_rate": 8.002055634117578e-07,
+      "loss": 0.5088,
+      "step": 2415
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.20645302721542735,
+      "learning_rate": 7.753347387144294e-07,
+      "loss": 0.5126,
+      "step": 2420
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.20323590104576408,
+      "learning_rate": 7.508409463346389e-07,
+      "loss": 0.5234,
+      "step": 2425
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.20483041641048474,
+      "learning_rate": 7.26725187387446e-07,
+      "loss": 0.5207,
+      "step": 2430
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.20363185231425762,
+      "learning_rate": 7.029884475368542e-07,
+      "loss": 0.5234,
+      "step": 2435
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.19585624352673048,
+      "learning_rate": 6.796316969555205e-07,
+      "loss": 0.516,
+      "step": 2440
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.21163098285472737,
+      "learning_rate": 6.566558902851161e-07,
+      "loss": 0.5382,
+      "step": 2445
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.2061275767234072,
+      "learning_rate": 6.340619665972847e-07,
+      "loss": 0.5252,
+      "step": 2450
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.2050927030534903,
+      "learning_rate": 6.118508493552866e-07,
+      "loss": 0.5081,
+      "step": 2455
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.20411513952463778,
+      "learning_rate": 5.900234463762367e-07,
+      "loss": 0.5248,
+      "step": 2460
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.20399794959320638,
+      "learning_rate": 5.685806497940027e-07,
+      "loss": 0.5163,
+      "step": 2465
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.20891752353282228,
+      "learning_rate": 5.475233360227516e-07,
+      "loss": 0.529,
+      "step": 2470
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.2005044795674912,
+      "learning_rate": 5.268523657211188e-07,
+      "loss": 0.5009,
+      "step": 2475
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.2046930603550785,
+      "learning_rate": 5.065685837570312e-07,
+      "loss": 0.5165,
+      "step": 2480
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.20175610856641593,
+      "learning_rate": 4.866728191731829e-07,
+      "loss": 0.5182,
+      "step": 2485
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.2030309299250094,
+      "learning_rate": 4.671658851531424e-07,
+      "loss": 0.5199,
+      "step": 2490
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.1914622288737903,
+      "learning_rate": 4.480485789881217e-07,
+      "loss": 0.5177,
+      "step": 2495
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.19668048668936855,
+      "learning_rate": 4.293216820443891e-07,
+      "loss": 0.5308,
+      "step": 2500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.22039481521735169,
+      "learning_rate": 4.109859597313237e-07,
+      "loss": 0.5283,
+      "step": 2505
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.20757846010886538,
+      "learning_rate": 3.9304216147014853e-07,
+      "loss": 0.5347,
+      "step": 2510
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.20740377627342962,
+      "learning_rate": 3.7549102066328226e-07,
+      "loss": 0.5307,
+      "step": 2515
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.2100472925176084,
+      "learning_rate": 3.5833325466437697e-07,
+      "loss": 0.5223,
+      "step": 2520
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.20177360779386036,
+      "learning_rate": 3.4156956474898805e-07,
+      "loss": 0.5255,
+      "step": 2525
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.20707380368033076,
+      "learning_rate": 3.2520063608592165e-07,
+      "loss": 0.5122,
+      "step": 2530
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.19965994990493274,
+      "learning_rate": 3.0922713770922155e-07,
+      "loss": 0.5214,
+      "step": 2535
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.20324516199000714,
+      "learning_rate": 2.9364972249082747e-07,
+      "loss": 0.5145,
+      "step": 2540
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.20150097372860662,
+      "learning_rate": 2.7846902711389236e-07,
+      "loss": 0.5132,
+      "step": 2545
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.2051450132081192,
+      "learning_rate": 2.636856720467573e-07,
+      "loss": 0.5128,
+      "step": 2550
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.20266490344541718,
+      "learning_rate": 2.493002615175977e-07,
+      "loss": 0.5122,
+      "step": 2555
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.20236603858533658,
+      "learning_rate": 2.3531338348971366e-07,
+      "loss": 0.5327,
+      "step": 2560
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.20530608079603682,
+      "learning_rate": 2.217256096375131e-07,
+      "loss": 0.5099,
+      "step": 2565
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.2000522109375465,
+      "learning_rate": 2.0853749532314006e-07,
+      "loss": 0.5299,
+      "step": 2570
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.20808661956102248,
+      "learning_rate": 1.9574957957377294e-07,
+      "loss": 0.5225,
+      "step": 2575
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.2026575467689292,
+      "learning_rate": 1.8336238505959892e-07,
+      "loss": 0.5286,
+      "step": 2580
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.2043520049010144,
+      "learning_rate": 1.7137641807244754e-07,
+      "loss": 0.5218,
+      "step": 2585
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.20057729109993613,
+      "learning_rate": 1.5979216850509848e-07,
+      "loss": 0.5225,
+      "step": 2590
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.20086887199752657,
+      "learning_rate": 1.4861010983126202e-07,
+      "loss": 0.521,
+      "step": 2595
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.20600288196892624,
+      "learning_rate": 1.3783069908621772e-07,
+      "loss": 0.5233,
+      "step": 2600
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.2032590701020277,
+      "learning_rate": 1.274543768481451e-07,
+      "loss": 0.5298,
+      "step": 2605
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.19937401805144794,
+      "learning_rate": 1.1748156722011128e-07,
+      "loss": 0.5012,
+      "step": 2610
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.2021678865177686,
+      "learning_rate": 1.0791267781273263e-07,
+      "loss": 0.5242,
+      "step": 2615
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.20777988223157803,
+      "learning_rate": 9.874809972752697e-08,
+      "loss": 0.5293,
+      "step": 2620
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.20368366862991866,
+      "learning_rate": 8.99882075409153e-08,
+      "loss": 0.5153,
+      "step": 2625
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.20787994510400237,
+      "learning_rate": 8.16333592889207e-08,
+      "loss": 0.5345,
+      "step": 2630
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.20946081246812162,
+      "learning_rate": 7.368389645252772e-08,
+      "loss": 0.5229,
+      "step": 2635
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.20571639236209135,
+      "learning_rate": 6.61401439437348e-08,
+      "loss": 0.5151,
+      "step": 2640
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.21182777269953695,
+      "learning_rate": 5.9002410092262593e-08,
+      "loss": 0.5207,
+      "step": 2645
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.1955808209671619,
+      "learning_rate": 5.227098663296404e-08,
+      "loss": 0.5073,
+      "step": 2650
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.20179292685793432,
+      "learning_rate": 4.594614869388947e-08,
+      "loss": 0.5212,
+      "step": 2655
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.20236344715337046,
+      "learning_rate": 4.002815478505007e-08,
+      "loss": 0.5208,
+      "step": 2660
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.2112521255560089,
+      "learning_rate": 3.451724678784518e-08,
+      "loss": 0.5155,
+      "step": 2665
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.1988319336416073,
+      "learning_rate": 2.9413649945182475e-08,
+      "loss": 0.5149,
+      "step": 2670
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.2393477878018782,
+      "learning_rate": 2.47175728522675e-08,
+      "loss": 0.5196,
+      "step": 2675
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.1989296468037607,
+      "learning_rate": 2.0429207448078302e-08,
+      "loss": 0.4954,
+      "step": 2680
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.21328717756995305,
+      "learning_rate": 1.654872900752169e-08,
+      "loss": 0.5211,
+      "step": 2685
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.2043004896942241,
+      "learning_rate": 1.3076296134271194e-08,
+      "loss": 0.5298,
+      "step": 2690
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.20203087493728625,
+      "learning_rate": 1.0012050754277802e-08,
+      "loss": 0.5142,
+      "step": 2695
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.20708771065311932,
+      "learning_rate": 7.356118109977939e-09,
+      "loss": 0.5352,
+      "step": 2700
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.20602452029141277,
+      "learning_rate": 5.108606755168666e-09,
+      "loss": 0.528,
+      "step": 2705
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.20878635383712413,
+      "learning_rate": 3.269608550571235e-09,
+      "loss": 0.5155,
+      "step": 2710
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.1972058695515002,
+      "learning_rate": 1.839198660079644e-09,
+      "loss": 0.5121,
+      "step": 2715
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.2017859212074039,
+      "learning_rate": 8.174355476864293e-10,
+      "loss": 0.5193,
+      "step": 2720
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.20180951712274753,
+      "learning_rate": 2.0436097509235475e-10,
+      "loss": 0.5331,
+      "step": 2725
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.2006750130728712,
+      "learning_rate": 0.0,
+      "loss": 0.5227,
+      "step": 2730
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6613607406616211,
+      "eval_runtime": 13.2749,
+      "eval_samples_per_second": 103.805,
+      "eval_steps_per_second": 0.829,
+      "step": 2730
+    },
+    {
+      "epoch": 3.0,
+      "step": 2730,
+      "total_flos": 1.183665069490176e+16,
+      "train_loss": 0.6159939037574517,
+      "train_runtime": 13745.4884,
+      "train_samples_per_second": 25.399,
+      "train_steps_per_second": 0.199
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1.183665069490176e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63228e190b2d1032f998e66c70c0651d7ad3fcdfc67be84ddc5308fe5644eca5
+size 6520