Model save

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: BramVanroy/fietje-2b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: fietje-2b-sft
+  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. -->
+
+# fietje-2b-sft
+
+This model is a fine-tuned version of [BramVanroy/fietje-2b](https://huggingface.co/BramVanroy/fietje-2b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8818
+
+## 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: 6e-05
+- train_batch_size: 42
+- eval_batch_size: 42
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 672
+- total_eval_batch_size: 672
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9325        | 1.0   | 178  | 0.9060          |
+| 0.8687        | 2.0   | 356  | 0.8850          |
+| 0.8385        | 3.0   | 534  | 0.8818          |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9222131907270196,
+    "train_runtime": 33956.1835,
+    "train_samples": 201571,
+    "train_samples_per_second": 10.545,
+    "train_steps_per_second": 0.016
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50295,
+  "eos_token_id": 50296,
+  "pad_token_id": 50296,
+  "transformers_version": "4.39.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5fdc0699ada9a30d5743b6cd7fe8fb8d47fa11d8aab9ad200274f4506d5377
+size 4990961488

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51beda028780b6ce995b6aaf725a35a176df8cc2acec3649e095dfb5f5fc660
+size 559207842

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 5550119154
+  },
+  "weight_map": {
+    "lm_head.bias": "model-00002-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9222131907270196,
+    "train_runtime": 33956.1835,
+    "train_samples": 201571,
+    "train_samples_per_second": 10.545,
+    "train_steps_per_second": 0.016
+}

trainer_state.json

@@ -0,0 +1,3792 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 534,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 307.2925252001398,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 2.14,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 348.5579299962218,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 2.1592,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 295.8217735171242,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.1112,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 320.95278420676283,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 2.0727,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 273.6994356101882,
+      "learning_rate": 5.555555555555555e-06,
+      "loss": 1.8522,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 137.18652764811333,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5844,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.105539597979915,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.4424,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.0951798632526275,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.4244,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.6078027918916717,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 1.3763,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.9798839986563381,
+      "learning_rate": 1.111111111111111e-05,
+      "loss": 1.3583,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.065159602417454,
+      "learning_rate": 1.2222222222222222e-05,
+      "loss": 1.3335,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.3002391180584008,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.309,
+      "step": 12
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.2825778137111357,
+      "learning_rate": 1.4444444444444444e-05,
+      "loss": 1.2932,
+      "step": 13
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0205928394685457,
+      "learning_rate": 1.5555555555555555e-05,
+      "loss": 1.2689,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3373431587246087,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2489,
+      "step": 15
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.8043774075647928,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.2302,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8741531962350515,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.2195,
+      "step": 17
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.7028376256413013,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 1.2027,
+      "step": 18
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.6648050831010063,
+      "learning_rate": 2.111111111111111e-05,
+      "loss": 1.1887,
+      "step": 19
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.7354468182477213,
+      "learning_rate": 2.222222222222222e-05,
+      "loss": 1.1704,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.7839624362161648,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.1654,
+      "step": 21
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.7752033041911668,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.1544,
+      "step": 22
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.7396236066452132,
+      "learning_rate": 2.5555555555555557e-05,
+      "loss": 1.138,
+      "step": 23
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.748517600591021,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.133,
+      "step": 24
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.7065074963471533,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.1119,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7289352652301433,
+      "learning_rate": 2.8888888888888888e-05,
+      "loss": 1.1132,
+      "step": 26
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7324972388581718,
+      "learning_rate": 3e-05,
+      "loss": 1.1008,
+      "step": 27
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7020306466156484,
+      "learning_rate": 3.111111111111111e-05,
+      "loss": 1.1067,
+      "step": 28
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7080095311543003,
+      "learning_rate": 3.222222222222223e-05,
+      "loss": 1.1028,
+      "step": 29
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.7149252394051553,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.0953,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.7285982439983161,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 1.0859,
+      "step": 31
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.7057181936211316,
+      "learning_rate": 3.555555555555555e-05,
+      "loss": 1.0829,
+      "step": 32
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.718290068719298,
+      "learning_rate": 3.666666666666667e-05,
+      "loss": 1.0658,
+      "step": 33
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.6998775916382852,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 1.0687,
+      "step": 34
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6851057008807085,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.0701,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6724489509428345,
+      "learning_rate": 3.9999999999999996e-05,
+      "loss": 1.0675,
+      "step": 36
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.6480552435697329,
+      "learning_rate": 4.1111111111111116e-05,
+      "loss": 1.0537,
+      "step": 37
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.6383559954105056,
+      "learning_rate": 4.222222222222222e-05,
+      "loss": 1.0463,
+      "step": 38
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6029067517028285,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 1.0422,
+      "step": 39
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5709974683191396,
+      "learning_rate": 4.444444444444444e-05,
+      "loss": 1.037,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5363586512263623,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 1.0249,
+      "step": 41
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5064701225673895,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.0269,
+      "step": 42
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4492710010511058,
+      "learning_rate": 4.777777777777778e-05,
+      "loss": 1.014,
+      "step": 43
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.4154607764986574,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 1.0209,
+      "step": 44
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3647804068160132,
+      "learning_rate": 5e-05,
+      "loss": 1.019,
+      "step": 45
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.3247880218369176,
+      "learning_rate": 5.1111111111111115e-05,
+      "loss": 1.0142,
+      "step": 46
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.3054048294238843,
+      "learning_rate": 5.222222222222222e-05,
+      "loss": 1.005,
+      "step": 47
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2911566588563454,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.0182,
+      "step": 48
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.30175247842711633,
+      "learning_rate": 5.4444444444444446e-05,
+      "loss": 1.003,
+      "step": 49
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2957438299690764,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 1.0018,
+      "step": 50
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.222811420448816,
+      "learning_rate": 5.6666666666666664e-05,
+      "loss": 0.9982,
+      "step": 51
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.19282721337866324,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 1.003,
+      "step": 52
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2271139316205582,
+      "learning_rate": 5.888888888888889e-05,
+      "loss": 0.9884,
+      "step": 53
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.22400303611020278,
+      "learning_rate": 6e-05,
+      "loss": 0.9933,
+      "step": 54
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.2640000653332148,
+      "learning_rate": 5.999935744992388e-05,
+      "loss": 0.9898,
+      "step": 55
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.29683962789566454,
+      "learning_rate": 5.999742982722021e-05,
+      "loss": 0.9894,
+      "step": 56
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.23953312072588218,
+      "learning_rate": 5.999421721446195e-05,
+      "loss": 0.9891,
+      "step": 57
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.22760431232110737,
+      "learning_rate": 5.9989719749266715e-05,
+      "loss": 0.9794,
+      "step": 58
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.28069530624064654,
+      "learning_rate": 5.998393762429097e-05,
+      "loss": 0.9827,
+      "step": 59
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.33248489828390104,
+      "learning_rate": 5.997687108722169e-05,
+      "loss": 0.9829,
+      "step": 60
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.37460157299926583,
+      "learning_rate": 5.9968520440765807e-05,
+      "loss": 0.9865,
+      "step": 61
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.40204606775328766,
+      "learning_rate": 5.9958886042637214e-05,
+      "loss": 0.9872,
+      "step": 62
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.2760468657673376,
+      "learning_rate": 5.994796830554148e-05,
+      "loss": 0.9825,
+      "step": 63
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.25200297636338487,
+      "learning_rate": 5.9935767697158103e-05,
+      "loss": 0.9761,
+      "step": 64
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.3387334098621161,
+      "learning_rate": 5.992228474012056e-05,
+      "loss": 0.9724,
+      "step": 65
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.3352356569193807,
+      "learning_rate": 5.990752001199384e-05,
+      "loss": 0.9694,
+      "step": 66
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.25307126239627026,
+      "learning_rate": 5.989147414524976e-05,
+      "loss": 0.9751,
+      "step": 67
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.28603448445681706,
+      "learning_rate": 5.987414782723985e-05,
+      "loss": 0.9675,
+      "step": 68
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.2512510471162242,
+      "learning_rate": 5.985554180016591e-05,
+      "loss": 0.9713,
+      "step": 69
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.23308838498745504,
+      "learning_rate": 5.98356568610482e-05,
+      "loss": 0.9675,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2507676754613168,
+      "learning_rate": 5.981449386169134e-05,
+      "loss": 0.9768,
+      "step": 71
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.17834215895890057,
+      "learning_rate": 5.979205370864779e-05,
+      "loss": 0.9736,
+      "step": 72
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.22157097251518248,
+      "learning_rate": 5.976833736317901e-05,
+      "loss": 0.9761,
+      "step": 73
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.19478083716793773,
+      "learning_rate": 5.9743345841214316e-05,
+      "loss": 0.9578,
+      "step": 74
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.23929984172471444,
+      "learning_rate": 5.9717080213307314e-05,
+      "loss": 0.9637,
+      "step": 75
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1792504123152509,
+      "learning_rate": 5.968954160459011e-05,
+      "loss": 0.9694,
+      "step": 76
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1942820411854134,
+      "learning_rate": 5.966073119472502e-05,
+      "loss": 0.9654,
+      "step": 77
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.20225817833116058,
+      "learning_rate": 5.963065021785414e-05,
+      "loss": 0.9568,
+      "step": 78
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.17871245685588816,
+      "learning_rate": 5.9599299962546375e-05,
+      "loss": 0.9672,
+      "step": 79
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.19357967707631799,
+      "learning_rate": 5.956668177174234e-05,
+      "loss": 0.9581,
+      "step": 80
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.17703904963665285,
+      "learning_rate": 5.953279704269675e-05,
+      "loss": 0.9399,
+      "step": 81
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.18397738069475075,
+      "learning_rate": 5.949764722691864e-05,
+      "loss": 0.9582,
+      "step": 82
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1667458999382299,
+      "learning_rate": 5.9461233830109117e-05,
+      "loss": 0.9574,
+      "step": 83
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.15246629979305598,
+      "learning_rate": 5.9423558412096914e-05,
+      "loss": 0.9624,
+      "step": 84
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.147474418280348,
+      "learning_rate": 5.938462258677154e-05,
+      "loss": 0.9574,
+      "step": 85
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.18908685471550463,
+      "learning_rate": 5.934442802201417e-05,
+      "loss": 0.9559,
+      "step": 86
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.15962484297812873,
+      "learning_rate": 5.930297643962617e-05,
+      "loss": 0.9565,
+      "step": 87
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.15626218745541218,
+      "learning_rate": 5.926026961525538e-05,
+      "loss": 0.9669,
+      "step": 88
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16363056001381104,
+      "learning_rate": 5.921630937832001e-05,
+      "loss": 0.9575,
+      "step": 89
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.17266359267085402,
+      "learning_rate": 5.91710976119303e-05,
+      "loss": 0.9482,
+      "step": 90
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.16154285700465842,
+      "learning_rate": 5.9124636252807844e-05,
+      "loss": 0.9486,
+      "step": 91
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1505238744935054,
+      "learning_rate": 5.907692729120263e-05,
+      "loss": 0.9465,
+      "step": 92
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1665515957602505,
+      "learning_rate": 5.9027972770807796e-05,
+      "loss": 0.9458,
+      "step": 93
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.15288744931626277,
+      "learning_rate": 5.897777478867205e-05,
+      "loss": 0.9513,
+      "step": 94
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.13893588088386338,
+      "learning_rate": 5.892633549510988e-05,
+      "loss": 0.9517,
+      "step": 95
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.15518080707211024,
+      "learning_rate": 5.887365709360941e-05,
+      "loss": 0.956,
+      "step": 96
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.16735904200015367,
+      "learning_rate": 5.881974184073806e-05,
+      "loss": 0.9644,
+      "step": 97
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.16211582659946666,
+      "learning_rate": 5.876459204604579e-05,
+      "loss": 0.947,
+      "step": 98
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.16067404496452142,
+      "learning_rate": 5.8708210071966266e-05,
+      "loss": 0.9493,
+      "step": 99
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.16466229984590008,
+      "learning_rate": 5.8650598333715604e-05,
+      "loss": 0.9525,
+      "step": 100
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.15635651077742227,
+      "learning_rate": 5.8591759299188915e-05,
+      "loss": 0.9462,
+      "step": 101
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.1445739463712597,
+      "learning_rate": 5.853169548885461e-05,
+      "loss": 0.9557,
+      "step": 102
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.16706069442335733,
+      "learning_rate": 5.847040947564642e-05,
+      "loss": 0.9571,
+      "step": 103
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.14383289999902457,
+      "learning_rate": 5.8407903884853173e-05,
+      "loss": 0.9452,
+      "step": 104
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.1409356084289515,
+      "learning_rate": 5.8344181394006345e-05,
+      "loss": 0.9452,
+      "step": 105
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1697312533943109,
+      "learning_rate": 5.827924473276536e-05,
+      "loss": 0.9567,
+      "step": 106
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.17531082504359882,
+      "learning_rate": 5.821309668280065e-05,
+      "loss": 0.9462,
+      "step": 107
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1639474813042821,
+      "learning_rate": 5.814574007767453e-05,
+      "loss": 0.9485,
+      "step": 108
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.17850681384081132,
+      "learning_rate": 5.807717780271977e-05,
+      "loss": 0.9366,
+      "step": 109
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.16125613154173873,
+      "learning_rate": 5.800741279491605e-05,
+      "loss": 0.9451,
+      "step": 110
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.197900179672024,
+      "learning_rate": 5.7936448042764106e-05,
+      "loss": 0.9495,
+      "step": 111
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.21076815721637063,
+      "learning_rate": 5.7864286586157726e-05,
+      "loss": 0.9435,
+      "step": 112
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.19782059920889028,
+      "learning_rate": 5.7790931516253545e-05,
+      "loss": 0.9416,
+      "step": 113
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1836244550876009,
+      "learning_rate": 5.7716385975338605e-05,
+      "loss": 0.9466,
+      "step": 114
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.1613256822257701,
+      "learning_rate": 5.764065315669578e-05,
+      "loss": 0.9513,
+      "step": 115
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.16741350820768655,
+      "learning_rate": 5.756373630446695e-05,
+      "loss": 0.9418,
+      "step": 116
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.18843157688751017,
+      "learning_rate": 5.748563871351408e-05,
+      "loss": 0.945,
+      "step": 117
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.15069085597597218,
+      "learning_rate": 5.7406363729278026e-05,
+      "loss": 0.9466,
+      "step": 118
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.16662142102625724,
+      "learning_rate": 5.7325914747635275e-05,
+      "loss": 0.9486,
+      "step": 119
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.19590155354881233,
+      "learning_rate": 5.724429521475244e-05,
+      "loss": 0.9435,
+      "step": 120
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.15881882311241918,
+      "learning_rate": 5.716150862693866e-05,
+      "loss": 0.9466,
+      "step": 121
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.14283264252478434,
+      "learning_rate": 5.707755853049582e-05,
+      "loss": 0.9412,
+      "step": 122
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.16782472517291772,
+      "learning_rate": 5.699244852156665e-05,
+      "loss": 0.9382,
+      "step": 123
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.16548141172284359,
+      "learning_rate": 5.690618224598065e-05,
+      "loss": 0.9479,
+      "step": 124
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.13809707490800946,
+      "learning_rate": 5.681876339909797e-05,
+      "loss": 0.9429,
+      "step": 125
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.18656335425800988,
+      "learning_rate": 5.673019572565103e-05,
+      "loss": 0.9381,
+      "step": 126
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1732296780937527,
+      "learning_rate": 5.664048301958422e-05,
+      "loss": 0.9431,
+      "step": 127
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.14221356678314365,
+      "learning_rate": 5.654962912389126e-05,
+      "loss": 0.9523,
+      "step": 128
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.15119656927035072,
+      "learning_rate": 5.645763793045065e-05,
+      "loss": 0.9392,
+      "step": 129
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.14464956279442504,
+      "learning_rate": 5.636451337985896e-05,
+      "loss": 0.9384,
+      "step": 130
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.13140580588464784,
+      "learning_rate": 5.627025946126199e-05,
+      "loss": 0.9372,
+      "step": 131
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.14493562139149813,
+      "learning_rate": 5.617488021218392e-05,
+      "loss": 0.9358,
+      "step": 132
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.14893216335321577,
+      "learning_rate": 5.6078379718354315e-05,
+      "loss": 0.9419,
+      "step": 133
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.14722396099871643,
+      "learning_rate": 5.5980762113533166e-05,
+      "loss": 0.944,
+      "step": 134
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1484388680331261,
+      "learning_rate": 5.588203157933376e-05,
+      "loss": 0.946,
+      "step": 135
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.14453486799975523,
+      "learning_rate": 5.578219234504359e-05,
+      "loss": 0.9502,
+      "step": 136
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.13849264435281988,
+      "learning_rate": 5.568124868744315e-05,
+      "loss": 0.9339,
+      "step": 137
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16199659629172095,
+      "learning_rate": 5.557920493062277e-05,
+      "loss": 0.9238,
+      "step": 138
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16192446153254933,
+      "learning_rate": 5.547606544579737e-05,
+      "loss": 0.9336,
+      "step": 139
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.14648464155352814,
+      "learning_rate": 5.5371834651119204e-05,
+      "loss": 0.9305,
+      "step": 140
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1383162638141149,
+      "learning_rate": 5.5266517011488596e-05,
+      "loss": 0.9391,
+      "step": 141
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1543998232523172,
+      "learning_rate": 5.5160117038362726e-05,
+      "loss": 0.9366,
+      "step": 142
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15730672921508043,
+      "learning_rate": 5.5052639289562294e-05,
+      "loss": 0.9346,
+      "step": 143
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.13879299352222021,
+      "learning_rate": 5.494408836907636e-05,
+      "loss": 0.9364,
+      "step": 144
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.15487093688296455,
+      "learning_rate": 5.483446892686507e-05,
+      "loss": 0.9246,
+      "step": 145
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.14401066674945762,
+      "learning_rate": 5.472378565866047e-05,
+      "loss": 0.9361,
+      "step": 146
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.14277478926628612,
+      "learning_rate": 5.461204330576541e-05,
+      "loss": 0.9389,
+      "step": 147
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.16131149816932222,
+      "learning_rate": 5.4499246654850374e-05,
+      "loss": 0.9371,
+      "step": 148
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.17407874387998404,
+      "learning_rate": 5.4385400537748465e-05,
+      "loss": 0.9372,
+      "step": 149
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.17636478629943686,
+      "learning_rate": 5.427050983124843e-05,
+      "loss": 0.9343,
+      "step": 150
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.16977563161518314,
+      "learning_rate": 5.4154579456885744e-05,
+      "loss": 0.9281,
+      "step": 151
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.14318477872489785,
+      "learning_rate": 5.403761438073182e-05,
+      "loss": 0.9365,
+      "step": 152
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1397942734256781,
+      "learning_rate": 5.3919619613181215e-05,
+      "loss": 0.9469,
+      "step": 153
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.137963649770748,
+      "learning_rate": 5.3800600208737054e-05,
+      "loss": 0.9359,
+      "step": 154
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.15171364959388206,
+      "learning_rate": 5.3680561265794496e-05,
+      "loss": 0.9269,
+      "step": 155
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.14709787438935637,
+      "learning_rate": 5.3559507926422344e-05,
+      "loss": 0.9383,
+      "step": 156
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.12890500807018168,
+      "learning_rate": 5.343744537614276e-05,
+      "loss": 0.924,
+      "step": 157
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.11549683107184264,
+      "learning_rate": 5.331437884370913e-05,
+      "loss": 0.9283,
+      "step": 158
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.15022761689747757,
+      "learning_rate": 5.319031360088211e-05,
+      "loss": 0.9307,
+      "step": 159
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.15714839886122223,
+      "learning_rate": 5.306525496220379e-05,
+      "loss": 0.935,
+      "step": 160
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.16859132275494298,
+      "learning_rate": 5.293920828477001e-05,
+      "loss": 0.9239,
+      "step": 161
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.13633581062447336,
+      "learning_rate": 5.281217896800093e-05,
+      "loss": 0.9414,
+      "step": 162
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1513556776118746,
+      "learning_rate": 5.268417245340968e-05,
+      "loss": 0.9338,
+      "step": 163
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1757338104436492,
+      "learning_rate": 5.255519422436932e-05,
+      "loss": 0.9351,
+      "step": 164
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.19112425290854476,
+      "learning_rate": 5.242524980587791e-05,
+      "loss": 0.9333,
+      "step": 165
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.17979027309488244,
+      "learning_rate": 5.2294344764321825e-05,
+      "loss": 0.9179,
+      "step": 166
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.16529910589891425,
+      "learning_rate": 5.2162484707237387e-05,
+      "loss": 0.9356,
+      "step": 167
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.20692577816446356,
+      "learning_rate": 5.202967528307057e-05,
+      "loss": 0.9276,
+      "step": 168
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.197154695709334,
+      "learning_rate": 5.1895922180935066e-05,
+      "loss": 0.9303,
+      "step": 169
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14150974456692325,
+      "learning_rate": 5.176123113036863e-05,
+      "loss": 0.9364,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.15101923044037124,
+      "learning_rate": 5.162560790108756e-05,
+      "loss": 0.9219,
+      "step": 171
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.19585100899813354,
+      "learning_rate": 5.148905830273964e-05,
+      "loss": 0.9282,
+      "step": 172
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.16466476745138203,
+      "learning_rate": 5.135158818465514e-05,
+      "loss": 0.9267,
+      "step": 173
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.13928826936678446,
+      "learning_rate": 5.1213203435596425e-05,
+      "loss": 0.9204,
+      "step": 174
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.16777686357665667,
+      "learning_rate": 5.107390998350555e-05,
+      "loss": 0.9209,
+      "step": 175
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.13941558577566035,
+      "learning_rate": 5.093371379525041e-05,
+      "loss": 0.933,
+      "step": 176
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1312376870568112,
+      "learning_rate": 5.079262087636908e-05,
+      "loss": 0.9273,
+      "step": 177
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13304976321730042,
+      "learning_rate": 5.0650637270812615e-05,
+      "loss": 0.9325,
+      "step": 178
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9060415029525757,
+      "eval_runtime": 367.2491,
+      "eval_samples_per_second": 35.657,
+      "eval_steps_per_second": 0.054,
+      "step": 178
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.14350856865519188,
+      "learning_rate": 5.0507769060686136e-05,
+      "loss": 0.8991,
+      "step": 179
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.14242795375317008,
+      "learning_rate": 5.036402236598826e-05,
+      "loss": 0.8819,
+      "step": 180
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.1481380625280409,
+      "learning_rate": 5.021940334434894e-05,
+      "loss": 0.9013,
+      "step": 181
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.14135102829732513,
+      "learning_rate": 5.007391819076575e-05,
+      "loss": 0.8876,
+      "step": 182
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.14410031273084303,
+      "learning_rate": 4.9927573137338456e-05,
+      "loss": 0.8962,
+      "step": 183
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.1356425817573695,
+      "learning_rate": 4.978037445300207e-05,
+      "loss": 0.8984,
+      "step": 184
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.15138222667915374,
+      "learning_rate": 4.963232844325832e-05,
+      "loss": 0.8934,
+      "step": 185
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.1476182931802454,
+      "learning_rate": 4.948344144990551e-05,
+      "loss": 0.8875,
+      "step": 186
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.1542666076621437,
+      "learning_rate": 4.933371985076692e-05,
+      "loss": 0.8916,
+      "step": 187
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.1522457621047058,
+      "learning_rate": 4.9183170059417543e-05,
+      "loss": 0.8924,
+      "step": 188
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.1401929471695145,
+      "learning_rate": 4.903179852490937e-05,
+      "loss": 0.8961,
+      "step": 189
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.1397403483022461,
+      "learning_rate": 4.887961173149513e-05,
+      "loss": 0.8841,
+      "step": 190
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.16199935662086337,
+      "learning_rate": 4.872661619835054e-05,
+      "loss": 0.8934,
+      "step": 191
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.17579997757407093,
+      "learning_rate": 4.857281847929503e-05,
+      "loss": 0.8912,
+      "step": 192
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.12918417902945037,
+      "learning_rate": 4.8418225162510994e-05,
+      "loss": 0.8955,
+      "step": 193
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.1357691544652963,
+      "learning_rate": 4.826284287026162e-05,
+      "loss": 0.8876,
+      "step": 194
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.13562412043146593,
+      "learning_rate": 4.8106678258607146e-05,
+      "loss": 0.8925,
+      "step": 195
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.14459127567703792,
+      "learning_rate": 4.794973801711977e-05,
+      "loss": 0.9046,
+      "step": 196
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.13612859027230298,
+      "learning_rate": 4.7792028868597114e-05,
+      "loss": 0.9008,
+      "step": 197
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.13139758263957305,
+      "learning_rate": 4.7633557568774194e-05,
+      "loss": 0.8883,
+      "step": 198
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.1332017950455885,
+      "learning_rate": 4.7474330906034067e-05,
+      "loss": 0.8872,
+      "step": 199
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.14003547669435232,
+      "learning_rate": 4.731435570111701e-05,
+      "loss": 0.8852,
+      "step": 200
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.12548622314931585,
+      "learning_rate": 4.7153638806828365e-05,
+      "loss": 0.8918,
+      "step": 201
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.1316324333822756,
+      "learning_rate": 4.699218710774499e-05,
+      "loss": 0.8911,
+      "step": 202
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.14152097644548858,
+      "learning_rate": 4.68300075199203e-05,
+      "loss": 0.8989,
+      "step": 203
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.1270200473456502,
+      "learning_rate": 4.6667106990588066e-05,
+      "loss": 0.8855,
+      "step": 204
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.1498866663693573,
+      "learning_rate": 4.650349249786481e-05,
+      "loss": 0.8915,
+      "step": 205
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.13575618100316017,
+      "learning_rate": 4.633917105045082e-05,
+      "loss": 0.8868,
+      "step": 206
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.12252093912010241,
+      "learning_rate": 4.617414968733002e-05,
+      "loss": 0.8993,
+      "step": 207
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.17129363052080313,
+      "learning_rate": 4.6008435477468346e-05,
+      "loss": 0.8979,
+      "step": 208
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.13086986947624585,
+      "learning_rate": 4.584203551951104e-05,
+      "loss": 0.9042,
+      "step": 209
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.1289023381093015,
+      "learning_rate": 4.567495694147847e-05,
+      "loss": 0.9079,
+      "step": 210
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.12646977417389443,
+      "learning_rate": 4.5507206900460824e-05,
+      "loss": 0.8805,
+      "step": 211
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.135408603034375,
+      "learning_rate": 4.533879258231156e-05,
+      "loss": 0.9036,
+      "step": 212
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.13151933660920634,
+      "learning_rate": 4.516972120133954e-05,
+      "loss": 0.8963,
+      "step": 213
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.14642201202966043,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8884,
+      "step": 214
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.13215103394112293,
+      "learning_rate": 4.4829636248584336e-05,
+      "loss": 0.8954,
+      "step": 215
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.14081499259661354,
+      "learning_rate": 4.4658637244908654e-05,
+      "loss": 0.9078,
+      "step": 216
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.13325013129319507,
+      "learning_rate": 4.448701031400112e-05,
+      "loss": 0.889,
+      "step": 217
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.14567267671389802,
+      "learning_rate": 4.431476280778825e-05,
+      "loss": 0.8896,
+      "step": 218
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.1530402998595256,
+      "learning_rate": 4.414190210477994e-05,
+      "loss": 0.8863,
+      "step": 219
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.11883142231327087,
+      "learning_rate": 4.396843560975334e-05,
+      "loss": 0.8956,
+      "step": 220
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.1441333083283775,
+      "learning_rate": 4.37943707534358e-05,
+      "loss": 0.8886,
+      "step": 221
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.14323097711463215,
+      "learning_rate": 4.3619714992186405e-05,
+      "loss": 0.8934,
+      "step": 222
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.14847369219388526,
+      "learning_rate": 4.344447580767668e-05,
+      "loss": 0.8993,
+      "step": 223
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.12999113661604003,
+      "learning_rate": 4.326866070657004e-05,
+      "loss": 0.8837,
+      "step": 224
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.1590097564167615,
+      "learning_rate": 4.309227722020026e-05,
+      "loss": 0.893,
+      "step": 225
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.13787186379941546,
+      "learning_rate": 4.291533290424886e-05,
+      "loss": 0.8873,
+      "step": 226
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.13561372365659452,
+      "learning_rate": 4.27378353384214e-05,
+      "loss": 0.8909,
+      "step": 227
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.12883018074018207,
+      "learning_rate": 4.2559792126122843e-05,
+      "loss": 0.8859,
+      "step": 228
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.13365029333191705,
+      "learning_rate": 4.238121089413184e-05,
+      "loss": 0.9062,
+      "step": 229
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.14359777080953676,
+      "learning_rate": 4.2202099292274015e-05,
+      "loss": 0.8991,
+      "step": 230
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.127263628452024,
+      "learning_rate": 4.2022464993094226e-05,
+      "loss": 0.8945,
+      "step": 231
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.15508442928638333,
+      "learning_rate": 4.184231569152802e-05,
+      "loss": 0.8971,
+      "step": 232
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.1498552324218163,
+      "learning_rate": 4.166165910457187e-05,
+      "loss": 0.891,
+      "step": 233
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.13461134175675027,
+      "learning_rate": 4.14805029709527e-05,
+      "loss": 0.8877,
+      "step": 234
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.14946029731016597,
+      "learning_rate": 4.1298855050796324e-05,
+      "loss": 0.8903,
+      "step": 235
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.13552355920453768,
+      "learning_rate": 4.1116723125295094e-05,
+      "loss": 0.8973,
+      "step": 236
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.14705105872966423,
+      "learning_rate": 4.09341149963745e-05,
+      "loss": 0.8982,
+      "step": 237
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.16411157831669457,
+      "learning_rate": 4.0751038486359e-05,
+      "loss": 0.8982,
+      "step": 238
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.13269150518487338,
+      "learning_rate": 4.056750143763701e-05,
+      "loss": 0.8895,
+      "step": 239
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.14962049546760073,
+      "learning_rate": 4.038351171232479e-05,
+      "loss": 0.8854,
+      "step": 240
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.16086784383385563,
+      "learning_rate": 4.019907719192982e-05,
+      "loss": 0.8964,
+      "step": 241
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.14444863678847175,
+      "learning_rate": 4.0014205777013125e-05,
+      "loss": 0.8847,
+      "step": 242
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.12452999678280204,
+      "learning_rate": 3.982890538685081e-05,
+      "loss": 0.8896,
+      "step": 243
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.15069697551107591,
+      "learning_rate": 3.964318395909485e-05,
+      "loss": 0.8986,
+      "step": 244
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.12577792786818992,
+      "learning_rate": 3.945704944943309e-05,
+      "loss": 0.884,
+      "step": 245
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.12286285953881854,
+      "learning_rate": 3.927050983124842e-05,
+      "loss": 0.8818,
+      "step": 246
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.13929979955363045,
+      "learning_rate": 3.908357309527724e-05,
+      "loss": 0.8866,
+      "step": 247
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.12285830808074812,
+      "learning_rate": 3.889624724926713e-05,
+      "loss": 0.8812,
+      "step": 248
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.12424668641448619,
+      "learning_rate": 3.870854031763387e-05,
+      "loss": 0.8928,
+      "step": 249
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.12954214774856612,
+      "learning_rate": 3.852046034111769e-05,
+      "loss": 0.8853,
+      "step": 250
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.1266013073117186,
+      "learning_rate": 3.8332015376438775e-05,
+      "loss": 0.8844,
+      "step": 251
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.12067596509699888,
+      "learning_rate": 3.8143213495952224e-05,
+      "loss": 0.8916,
+      "step": 252
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.11623622829833351,
+      "learning_rate": 3.795406278730224e-05,
+      "loss": 0.8859,
+      "step": 253
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.11551209984961364,
+      "learning_rate": 3.776457135307562e-05,
+      "loss": 0.8868,
+      "step": 254
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.11536856636572211,
+      "learning_rate": 3.757474731045474e-05,
+      "loss": 0.8828,
+      "step": 255
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.12375743852295125,
+      "learning_rate": 3.738459879086979e-05,
+      "loss": 0.8902,
+      "step": 256
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.12571384064192775,
+      "learning_rate": 3.71941339396505e-05,
+      "loss": 0.8885,
+      "step": 257
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.13081609687043957,
+      "learning_rate": 3.7003360915677164e-05,
+      "loss": 0.8954,
+      "step": 258
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.12420083605022122,
+      "learning_rate": 3.68122878910312e-05,
+      "loss": 0.8914,
+      "step": 259
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.13533339586556395,
+      "learning_rate": 3.6620923050645045e-05,
+      "loss": 0.8901,
+      "step": 260
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.11714010649732222,
+      "learning_rate": 3.6429274591951526e-05,
+      "loss": 0.899,
+      "step": 261
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.13060719113804842,
+      "learning_rate": 3.6237350724532775e-05,
+      "loss": 0.8987,
+      "step": 262
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.11664362421142428,
+      "learning_rate": 3.6045159669768514e-05,
+      "loss": 0.8835,
+      "step": 263
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.12473979951909206,
+      "learning_rate": 3.5852709660483855e-05,
+      "loss": 0.8824,
+      "step": 264
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.12297968050330141,
+      "learning_rate": 3.566000894059666e-05,
+      "loss": 0.8863,
+      "step": 265
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.13406322104382662,
+      "learning_rate": 3.5467065764764434e-05,
+      "loss": 0.8884,
+      "step": 266
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.12098972585519244,
+      "learning_rate": 3.527388839803064e-05,
+      "loss": 0.8857,
+      "step": 267
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.12310957119462022,
+      "learning_rate": 3.508048511547073e-05,
+      "loss": 0.8835,
+      "step": 268
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.11925523073706316,
+      "learning_rate": 3.4886864201837666e-05,
+      "loss": 0.8814,
+      "step": 269
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.13519867806471875,
+      "learning_rate": 3.469303395120693e-05,
+      "loss": 0.8783,
+      "step": 270
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.13530142559876104,
+      "learning_rate": 3.449900266662135e-05,
+      "loss": 0.8914,
+      "step": 271
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.14035599743211918,
+      "learning_rate": 3.430477865973538e-05,
+      "loss": 0.8884,
+      "step": 272
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.1405423762523139,
+      "learning_rate": 3.4110370250459046e-05,
+      "loss": 0.8803,
+      "step": 273
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.13704705253451768,
+      "learning_rate": 3.3915785766601555e-05,
+      "loss": 0.8773,
+      "step": 274
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.13457615586156477,
+      "learning_rate": 3.372103354351456e-05,
+      "loss": 0.8749,
+      "step": 275
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.11095858575701167,
+      "learning_rate": 3.3526121923735136e-05,
+      "loss": 0.8845,
+      "step": 276
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.13597531439993377,
+      "learning_rate": 3.333105925662833e-05,
+      "loss": 0.8928,
+      "step": 277
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.10509488873902952,
+      "learning_rate": 3.313585389802961e-05,
+      "loss": 0.8949,
+      "step": 278
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.13788943155574296,
+      "learning_rate": 3.294051420988683e-05,
+      "loss": 0.8848,
+      "step": 279
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.1128347052438993,
+      "learning_rate": 3.274504855990208e-05,
+      "loss": 0.89,
+      "step": 280
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.129080918181206,
+      "learning_rate": 3.254946532117325e-05,
+      "loss": 0.889,
+      "step": 281
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.13286996791565725,
+      "learning_rate": 3.235377287183535e-05,
+      "loss": 0.8852,
+      "step": 282
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 0.13354457708434664,
+      "learning_rate": 3.2157979594701584e-05,
+      "loss": 0.8788,
+      "step": 283
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.1336273953738305,
+      "learning_rate": 3.1962093876904294e-05,
+      "loss": 0.8878,
+      "step": 284
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.13151737304049846,
+      "learning_rate": 3.176612410953567e-05,
+      "loss": 0.8844,
+      "step": 285
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.1313340614662638,
+      "learning_rate": 3.157007868728832e-05,
+      "loss": 0.8882,
+      "step": 286
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 0.12675708891920084,
+      "learning_rate": 3.1373966008095624e-05,
+      "loss": 0.876,
+      "step": 287
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.13203447973990534,
+      "learning_rate": 3.117779447277206e-05,
+      "loss": 0.8866,
+      "step": 288
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.11627365297753998,
+      "learning_rate": 3.098157248465329e-05,
+      "loss": 0.8797,
+      "step": 289
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.12182727484026588,
+      "learning_rate": 3.07853084492362e-05,
+      "loss": 0.8867,
+      "step": 290
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.11050534350252515,
+      "learning_rate": 3.0589010773818843e-05,
+      "loss": 0.8714,
+      "step": 291
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.11908194959446168,
+      "learning_rate": 3.0392687867140333e-05,
+      "loss": 0.8805,
+      "step": 292
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.13824206533219605,
+      "learning_rate": 3.019634813902056e-05,
+      "loss": 0.8919,
+      "step": 293
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.10624499343917188,
+      "learning_rate": 3e-05,
+      "loss": 0.8872,
+      "step": 294
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.13416938377497178,
+      "learning_rate": 2.9803651860979446e-05,
+      "loss": 0.8882,
+      "step": 295
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.10669414306939697,
+      "learning_rate": 2.9607312132859672e-05,
+      "loss": 0.8886,
+      "step": 296
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.13304203015528449,
+      "learning_rate": 2.9410989226181155e-05,
+      "loss": 0.8858,
+      "step": 297
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.10943791939152962,
+      "learning_rate": 2.9214691550763813e-05,
+      "loss": 0.8862,
+      "step": 298
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.12414652355477009,
+      "learning_rate": 2.901842751534672e-05,
+      "loss": 0.8771,
+      "step": 299
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.12513686726484888,
+      "learning_rate": 2.882220552722795e-05,
+      "loss": 0.8884,
+      "step": 300
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.12991814913620842,
+      "learning_rate": 2.8626033991904384e-05,
+      "loss": 0.8912,
+      "step": 301
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.12469358939363877,
+      "learning_rate": 2.8429921312711687e-05,
+      "loss": 0.8755,
+      "step": 302
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.12431368690357643,
+      "learning_rate": 2.8233875890464327e-05,
+      "loss": 0.8758,
+      "step": 303
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.13987522452787626,
+      "learning_rate": 2.8037906123095708e-05,
+      "loss": 0.8869,
+      "step": 304
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.1238266615524893,
+      "learning_rate": 2.7842020405298415e-05,
+      "loss": 0.8783,
+      "step": 305
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.13322189651231403,
+      "learning_rate": 2.7646227128164657e-05,
+      "loss": 0.885,
+      "step": 306
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.11424790429145636,
+      "learning_rate": 2.7450534678826753e-05,
+      "loss": 0.8763,
+      "step": 307
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.13119287845211466,
+      "learning_rate": 2.725495144009793e-05,
+      "loss": 0.8767,
+      "step": 308
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.11575683203124575,
+      "learning_rate": 2.705948579011318e-05,
+      "loss": 0.8729,
+      "step": 309
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.14050128592489014,
+      "learning_rate": 2.6864146101970402e-05,
+      "loss": 0.8798,
+      "step": 310
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.11824436396680635,
+      "learning_rate": 2.6668940743371674e-05,
+      "loss": 0.8835,
+      "step": 311
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.12959459755274583,
+      "learning_rate": 2.6473878076264875e-05,
+      "loss": 0.8751,
+      "step": 312
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.11622350222131687,
+      "learning_rate": 2.627896645648545e-05,
+      "loss": 0.8931,
+      "step": 313
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.12314437146185572,
+      "learning_rate": 2.608421423339846e-05,
+      "loss": 0.8865,
+      "step": 314
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.11421490206501421,
+      "learning_rate": 2.5889629749540966e-05,
+      "loss": 0.8824,
+      "step": 315
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.1116631859004068,
+      "learning_rate": 2.5695221340264626e-05,
+      "loss": 0.8803,
+      "step": 316
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.10817788865943528,
+      "learning_rate": 2.5500997333378646e-05,
+      "loss": 0.8794,
+      "step": 317
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.11523773392162422,
+      "learning_rate": 2.530696604879307e-05,
+      "loss": 0.8832,
+      "step": 318
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.10502311886881133,
+      "learning_rate": 2.5113135798162342e-05,
+      "loss": 0.8816,
+      "step": 319
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.11059154509363399,
+      "learning_rate": 2.4919514884529262e-05,
+      "loss": 0.8787,
+      "step": 320
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.10388990188288608,
+      "learning_rate": 2.4726111601969365e-05,
+      "loss": 0.8824,
+      "step": 321
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.112930784152048,
+      "learning_rate": 2.4532934235235574e-05,
+      "loss": 0.8744,
+      "step": 322
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.11158721627694267,
+      "learning_rate": 2.433999105940335e-05,
+      "loss": 0.8847,
+      "step": 323
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 0.10338686368057544,
+      "learning_rate": 2.4147290339516156e-05,
+      "loss": 0.877,
+      "step": 324
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.1071678174366947,
+      "learning_rate": 2.3954840330231487e-05,
+      "loss": 0.884,
+      "step": 325
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.11226132071651221,
+      "learning_rate": 2.3762649275467226e-05,
+      "loss": 0.8747,
+      "step": 326
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.10930430786464529,
+      "learning_rate": 2.3570725408048483e-05,
+      "loss": 0.883,
+      "step": 327
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.10447714161398361,
+      "learning_rate": 2.337907694935497e-05,
+      "loss": 0.8797,
+      "step": 328
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.10888020274939628,
+      "learning_rate": 2.3187712108968808e-05,
+      "loss": 0.8779,
+      "step": 329
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.10873276266965934,
+      "learning_rate": 2.2996639084322848e-05,
+      "loss": 0.8716,
+      "step": 330
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.1051804371547165,
+      "learning_rate": 2.2805866060349513e-05,
+      "loss": 0.8925,
+      "step": 331
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.1073547759858754,
+      "learning_rate": 2.261540120913021e-05,
+      "loss": 0.8763,
+      "step": 332
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.10582013545010713,
+      "learning_rate": 2.242525268954526e-05,
+      "loss": 0.8801,
+      "step": 333
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.11360898822883193,
+      "learning_rate": 2.2235428646924375e-05,
+      "loss": 0.8861,
+      "step": 334
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.10517104031304181,
+      "learning_rate": 2.2045937212697755e-05,
+      "loss": 0.875,
+      "step": 335
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.11733374572446251,
+      "learning_rate": 2.1856786504047774e-05,
+      "loss": 0.8771,
+      "step": 336
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.10165485322637723,
+      "learning_rate": 2.1667984623561237e-05,
+      "loss": 0.8772,
+      "step": 337
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.12525581851096768,
+      "learning_rate": 2.147953965888232e-05,
+      "loss": 0.8893,
+      "step": 338
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.0991811666289482,
+      "learning_rate": 2.1291459682366136e-05,
+      "loss": 0.8777,
+      "step": 339
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.10828713812832842,
+      "learning_rate": 2.1103752750732875e-05,
+      "loss": 0.8834,
+      "step": 340
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.11106845149741414,
+      "learning_rate": 2.091642690472277e-05,
+      "loss": 0.874,
+      "step": 341
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.10116959541779709,
+      "learning_rate": 2.072949016875158e-05,
+      "loss": 0.8677,
+      "step": 342
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.11266898014907221,
+      "learning_rate": 2.054295055056692e-05,
+      "loss": 0.8926,
+      "step": 343
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 0.10220798261268464,
+      "learning_rate": 2.035681604090516e-05,
+      "loss": 0.8645,
+      "step": 344
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.1060144270004459,
+      "learning_rate": 2.0171094613149198e-05,
+      "loss": 0.8799,
+      "step": 345
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.10968581060830482,
+      "learning_rate": 1.9985794222986876e-05,
+      "loss": 0.8763,
+      "step": 346
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.11650138283261792,
+      "learning_rate": 1.980092280807017e-05,
+      "loss": 0.884,
+      "step": 347
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.10120824187747386,
+      "learning_rate": 1.9616488287675206e-05,
+      "loss": 0.8749,
+      "step": 348
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.11604072229024492,
+      "learning_rate": 1.9432498562362997e-05,
+      "loss": 0.8796,
+      "step": 349
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.10278157857112963,
+      "learning_rate": 1.924896151364099e-05,
+      "loss": 0.8793,
+      "step": 350
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.10712761878171682,
+      "learning_rate": 1.906588500362551e-05,
+      "loss": 0.8801,
+      "step": 351
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.10593823683108748,
+      "learning_rate": 1.888327687470491e-05,
+      "loss": 0.8783,
+      "step": 352
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.10348796531289477,
+      "learning_rate": 1.8701144949203677e-05,
+      "loss": 0.8786,
+      "step": 353
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.1074116166391481,
+      "learning_rate": 1.8519497029047307e-05,
+      "loss": 0.8778,
+      "step": 354
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.11058482340970019,
+      "learning_rate": 1.833834089542813e-05,
+      "loss": 0.8713,
+      "step": 355
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11020651242885636,
+      "learning_rate": 1.8157684308471988e-05,
+      "loss": 0.8687,
+      "step": 356
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8850164413452148,
+      "eval_runtime": 325.5979,
+      "eval_samples_per_second": 40.218,
+      "eval_steps_per_second": 0.061,
+      "step": 356
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.12003832997057942,
+      "learning_rate": 1.7977535006905776e-05,
+      "loss": 0.8401,
+      "step": 357
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.10675891351152236,
+      "learning_rate": 1.7797900707726e-05,
+      "loss": 0.8486,
+      "step": 358
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.13479155868015855,
+      "learning_rate": 1.761878910586816e-05,
+      "loss": 0.8508,
+      "step": 359
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.11372338660989749,
+      "learning_rate": 1.7440207873877165e-05,
+      "loss": 0.8415,
+      "step": 360
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.11106742867861737,
+      "learning_rate": 1.7262164661578614e-05,
+      "loss": 0.8546,
+      "step": 361
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.10946128209473692,
+      "learning_rate": 1.708466709575114e-05,
+      "loss": 0.8477,
+      "step": 362
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.10202238774555161,
+      "learning_rate": 1.6907722779799732e-05,
+      "loss": 0.8498,
+      "step": 363
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.11732343725531236,
+      "learning_rate": 1.6731339293429967e-05,
+      "loss": 0.8462,
+      "step": 364
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.10655979023984713,
+      "learning_rate": 1.6555524192323327e-05,
+      "loss": 0.8497,
+      "step": 365
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.1124168518526382,
+      "learning_rate": 1.6380285007813596e-05,
+      "loss": 0.8479,
+      "step": 366
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.10356449268514911,
+      "learning_rate": 1.6205629246564205e-05,
+      "loss": 0.852,
+      "step": 367
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.11466802705572018,
+      "learning_rate": 1.6031564390246658e-05,
+      "loss": 0.8469,
+      "step": 368
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.10022099638563725,
+      "learning_rate": 1.585809789522007e-05,
+      "loss": 0.8553,
+      "step": 369
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.11768853322439309,
+      "learning_rate": 1.5685237192211747e-05,
+      "loss": 0.8587,
+      "step": 370
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.09746799497107858,
+      "learning_rate": 1.551298968599889e-05,
+      "loss": 0.8461,
+      "step": 371
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.10423547308687264,
+      "learning_rate": 1.534136275509136e-05,
+      "loss": 0.8485,
+      "step": 372
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.1064669106822173,
+      "learning_rate": 1.517036375141567e-05,
+      "loss": 0.8495,
+      "step": 373
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.09616752021785893,
+      "learning_rate": 1.5000000000000007e-05,
+      "loss": 0.8438,
+      "step": 374
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.11068107117718663,
+      "learning_rate": 1.4830278798660467e-05,
+      "loss": 0.8563,
+      "step": 375
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.11633212251432552,
+      "learning_rate": 1.4661207417688442e-05,
+      "loss": 0.8541,
+      "step": 376
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.09985284219816701,
+      "learning_rate": 1.4492793099539175e-05,
+      "loss": 0.855,
+      "step": 377
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.11580112488775175,
+      "learning_rate": 1.4325043058521537e-05,
+      "loss": 0.8563,
+      "step": 378
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.0968466939956641,
+      "learning_rate": 1.415796448048896e-05,
+      "loss": 0.8526,
+      "step": 379
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.10786154660093858,
+      "learning_rate": 1.3991564522531655e-05,
+      "loss": 0.8485,
+      "step": 380
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.09923333146234646,
+      "learning_rate": 1.3825850312669992e-05,
+      "loss": 0.8513,
+      "step": 381
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.10427648708884239,
+      "learning_rate": 1.3660828949549189e-05,
+      "loss": 0.8486,
+      "step": 382
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.12292462282144442,
+      "learning_rate": 1.34965075021352e-05,
+      "loss": 0.8481,
+      "step": 383
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.1028967402644067,
+      "learning_rate": 1.3332893009411942e-05,
+      "loss": 0.8505,
+      "step": 384
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.10410540672946561,
+      "learning_rate": 1.3169992480079712e-05,
+      "loss": 0.8513,
+      "step": 385
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.09846244373078215,
+      "learning_rate": 1.3007812892255022e-05,
+      "loss": 0.8474,
+      "step": 386
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.1030135486730131,
+      "learning_rate": 1.2846361193171636e-05,
+      "loss": 0.8539,
+      "step": 387
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.09722668637542492,
+      "learning_rate": 1.2685644298882995e-05,
+      "loss": 0.8469,
+      "step": 388
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.10002106907707546,
+      "learning_rate": 1.2525669093965938e-05,
+      "loss": 0.8538,
+      "step": 389
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.1013552416026544,
+      "learning_rate": 1.2366442431225809e-05,
+      "loss": 0.8402,
+      "step": 390
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.10045607980672773,
+      "learning_rate": 1.2207971131402889e-05,
+      "loss": 0.8538,
+      "step": 391
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.10092477315351785,
+      "learning_rate": 1.2050261982880229e-05,
+      "loss": 0.8493,
+      "step": 392
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.09631205966968917,
+      "learning_rate": 1.1893321741392857e-05,
+      "loss": 0.844,
+      "step": 393
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.09480564837357011,
+      "learning_rate": 1.173715712973838e-05,
+      "loss": 0.8516,
+      "step": 394
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.10519104968879345,
+      "learning_rate": 1.1581774837489004e-05,
+      "loss": 0.8489,
+      "step": 395
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.09383687719586851,
+      "learning_rate": 1.1427181520704977e-05,
+      "loss": 0.8423,
+      "step": 396
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.09314803679639443,
+      "learning_rate": 1.1273383801649465e-05,
+      "loss": 0.855,
+      "step": 397
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.09785284085871111,
+      "learning_rate": 1.1120388268504882e-05,
+      "loss": 0.8592,
+      "step": 398
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.10014383710533643,
+      "learning_rate": 1.0968201475090638e-05,
+      "loss": 0.8527,
+      "step": 399
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.09342386714963961,
+      "learning_rate": 1.081682994058246e-05,
+      "loss": 0.8518,
+      "step": 400
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.09637941328010605,
+      "learning_rate": 1.0666280149233084e-05,
+      "loss": 0.8611,
+      "step": 401
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.09382962878187683,
+      "learning_rate": 1.0516558550094494e-05,
+      "loss": 0.8534,
+      "step": 402
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.09961841204532747,
+      "learning_rate": 1.036767155674169e-05,
+      "loss": 0.8616,
+      "step": 403
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.09436634787644145,
+      "learning_rate": 1.0219625546997936e-05,
+      "loss": 0.8484,
+      "step": 404
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.09434782225624004,
+      "learning_rate": 1.0072426862661559e-05,
+      "loss": 0.8543,
+      "step": 405
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.09240933321648483,
+      "learning_rate": 9.926081809234262e-06,
+      "loss": 0.8521,
+      "step": 406
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.09529963951322644,
+      "learning_rate": 9.780596655651062e-06,
+      "loss": 0.8502,
+      "step": 407
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.09779115542409987,
+      "learning_rate": 9.635977634011746e-06,
+      "loss": 0.8538,
+      "step": 408
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.0953318034742421,
+      "learning_rate": 9.492230939313859e-06,
+      "loss": 0.8462,
+      "step": 409
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.09533554193414427,
+      "learning_rate": 9.349362729187376e-06,
+      "loss": 0.8505,
+      "step": 410
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.09108747344016899,
+      "learning_rate": 9.207379123630928e-06,
+      "loss": 0.8364,
+      "step": 411
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.09157394780369447,
+      "learning_rate": 9.066286204749602e-06,
+      "loss": 0.8542,
+      "step": 412
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.09626988034418861,
+      "learning_rate": 8.926090016494452e-06,
+      "loss": 0.8395,
+      "step": 413
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.0932671686945301,
+      "learning_rate": 8.786796564403577e-06,
+      "loss": 0.8545,
+      "step": 414
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.09177787384063951,
+      "learning_rate": 8.648411815344862e-06,
+      "loss": 0.8478,
+      "step": 415
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.09283856078392008,
+      "learning_rate": 8.510941697260372e-06,
+      "loss": 0.8482,
+      "step": 416
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.09505027194291998,
+      "learning_rate": 8.374392098912435e-06,
+      "loss": 0.8515,
+      "step": 417
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.09061937534466419,
+      "learning_rate": 8.238768869631379e-06,
+      "loss": 0.8419,
+      "step": 418
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.09687410932411479,
+      "learning_rate": 8.104077819064939e-06,
+      "loss": 0.8455,
+      "step": 419
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.0919488286995836,
+      "learning_rate": 7.97032471692944e-06,
+      "loss": 0.8543,
+      "step": 420
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.0917348716297872,
+      "learning_rate": 7.837515292762618e-06,
+      "loss": 0.84,
+      "step": 421
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.0970295444546269,
+      "learning_rate": 7.70565523567817e-06,
+      "loss": 0.8483,
+      "step": 422
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.09120283035787119,
+      "learning_rate": 7.5747501941220924e-06,
+      "loss": 0.8495,
+      "step": 423
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.09237994609930707,
+      "learning_rate": 7.444805775630682e-06,
+      "loss": 0.8426,
+      "step": 424
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.0913397657548416,
+      "learning_rate": 7.315827546590318e-06,
+      "loss": 0.8512,
+      "step": 425
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.09498181364054688,
+      "learning_rate": 7.187821031999073e-06,
+      "loss": 0.8481,
+      "step": 426
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.10078078724917741,
+      "learning_rate": 7.0607917152299905e-06,
+      "loss": 0.8455,
+      "step": 427
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.09145562291129593,
+      "learning_rate": 6.9347450377962165e-06,
+      "loss": 0.8491,
+      "step": 428
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.09158338626328179,
+      "learning_rate": 6.8096863991178906e-06,
+      "loss": 0.8561,
+      "step": 429
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.09207229087759045,
+      "learning_rate": 6.685621156290873e-06,
+      "loss": 0.8467,
+      "step": 430
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.08985403499699009,
+      "learning_rate": 6.562554623857251e-06,
+      "loss": 0.8446,
+      "step": 431
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.09232970248222189,
+      "learning_rate": 6.440492073577659e-06,
+      "loss": 0.8412,
+      "step": 432
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.08869732511140344,
+      "learning_rate": 6.319438734205503e-06,
+      "loss": 0.8533,
+      "step": 433
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.09159355570132911,
+      "learning_rate": 6.199399791262949e-06,
+      "loss": 0.8426,
+      "step": 434
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.08776078153410961,
+      "learning_rate": 6.08038038681879e-06,
+      "loss": 0.8468,
+      "step": 435
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.08961006632692203,
+      "learning_rate": 5.962385619268184e-06,
+      "loss": 0.8443,
+      "step": 436
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.09327133481154146,
+      "learning_rate": 5.845420543114255e-06,
+      "loss": 0.8507,
+      "step": 437
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.08783358817348458,
+      "learning_rate": 5.72949016875158e-06,
+      "loss": 0.8444,
+      "step": 438
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.09080799921546491,
+      "learning_rate": 5.614599462251546e-06,
+      "loss": 0.8504,
+      "step": 439
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.09120455202673097,
+      "learning_rate": 5.500753345149633e-06,
+      "loss": 0.8511,
+      "step": 440
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.0883979066402917,
+      "learning_rate": 5.387956694234592e-06,
+      "loss": 0.8346,
+      "step": 441
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.08782824261068842,
+      "learning_rate": 5.2762143413395296e-06,
+      "loss": 0.8499,
+      "step": 442
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.09088620542561385,
+      "learning_rate": 5.165531073134936e-06,
+      "loss": 0.8496,
+      "step": 443
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.08784209719890995,
+      "learning_rate": 5.05591163092364e-06,
+      "loss": 0.8406,
+      "step": 444
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.09132953206887262,
+      "learning_rate": 4.9473607104377105e-06,
+      "loss": 0.8459,
+      "step": 445
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.08772978666632109,
+      "learning_rate": 4.839882961637282e-06,
+      "loss": 0.8505,
+      "step": 446
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.09985768462831238,
+      "learning_rate": 4.733482988511407e-06,
+      "loss": 0.8534,
+      "step": 447
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.08761275010174724,
+      "learning_rate": 4.628165348880804e-06,
+      "loss": 0.8524,
+      "step": 448
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.09041594806081453,
+      "learning_rate": 4.523934554202636e-06,
+      "loss": 0.8529,
+      "step": 449
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.08661829609254855,
+      "learning_rate": 4.4207950693772345e-06,
+      "loss": 0.8409,
+      "step": 450
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.0895302020625196,
+      "learning_rate": 4.3187513125568586e-06,
+      "loss": 0.8453,
+      "step": 451
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.08974158495627368,
+      "learning_rate": 4.217807654956419e-06,
+      "loss": 0.8427,
+      "step": 452
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.0881031632024463,
+      "learning_rate": 4.117968420666245e-06,
+      "loss": 0.8518,
+      "step": 453
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.08911231289710217,
+      "learning_rate": 4.019237886466839e-06,
+      "loss": 0.8479,
+      "step": 454
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.08758751320687048,
+      "learning_rate": 3.921620281645688e-06,
+      "loss": 0.8428,
+      "step": 455
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.08762936227381564,
+      "learning_rate": 3.825119787816085e-06,
+      "loss": 0.8541,
+      "step": 456
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.09070004531926247,
+      "learning_rate": 3.7297405387380066e-06,
+      "loss": 0.8606,
+      "step": 457
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.0901394728812162,
+      "learning_rate": 3.635486620141042e-06,
+      "loss": 0.8439,
+      "step": 458
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.09035508650424855,
+      "learning_rate": 3.542362069549352e-06,
+      "loss": 0.8597,
+      "step": 459
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.08987208626466826,
+      "learning_rate": 3.450370876108747e-06,
+      "loss": 0.8549,
+      "step": 460
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.08584439292379578,
+      "learning_rate": 3.3595169804157834e-06,
+      "loss": 0.8511,
+      "step": 461
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.0885850408197027,
+      "learning_rate": 3.2698042743489666e-06,
+      "loss": 0.8538,
+      "step": 462
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.09187965878611364,
+      "learning_rate": 3.1812366009020366e-06,
+      "loss": 0.8509,
+      "step": 463
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.08932729014366118,
+      "learning_rate": 3.0938177540193523e-06,
+      "loss": 0.8422,
+      "step": 464
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.0850824069799195,
+      "learning_rate": 3.0075514784333613e-06,
+      "loss": 0.8388,
+      "step": 465
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.08738926155401434,
+      "learning_rate": 2.922441469504188e-06,
+      "loss": 0.8561,
+      "step": 466
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.08920484001133727,
+      "learning_rate": 2.8384913730613404e-06,
+      "loss": 0.8557,
+      "step": 467
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.08819170118822395,
+      "learning_rate": 2.7557047852475594e-06,
+      "loss": 0.858,
+      "step": 468
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.08869175897009467,
+      "learning_rate": 2.674085252364723e-06,
+      "loss": 0.8536,
+      "step": 469
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.09053609127800862,
+      "learning_rate": 2.5936362707219708e-06,
+      "loss": 0.8483,
+      "step": 470
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.08867818730722615,
+      "learning_rate": 2.5143612864859246e-06,
+      "loss": 0.8532,
+      "step": 471
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.09139340482992017,
+      "learning_rate": 2.4362636955330543e-06,
+      "loss": 0.8498,
+      "step": 472
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.09525892817222975,
+      "learning_rate": 2.3593468433042278e-06,
+      "loss": 0.8529,
+      "step": 473
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.08789827680089286,
+      "learning_rate": 2.2836140246613977e-06,
+      "loss": 0.8521,
+      "step": 474
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.08648818427629963,
+      "learning_rate": 2.209068483746457e-06,
+      "loss": 0.8422,
+      "step": 475
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.08960144249428664,
+      "learning_rate": 2.135713413842273e-06,
+      "loss": 0.8505,
+      "step": 476
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.08754870519933383,
+      "learning_rate": 2.063551957235893e-06,
+      "loss": 0.8402,
+      "step": 477
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.08550557755721046,
+      "learning_rate": 1.992587205083951e-06,
+      "loss": 0.8575,
+      "step": 478
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.08826896212264684,
+      "learning_rate": 1.922822197280234e-06,
+      "loss": 0.8541,
+      "step": 479
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.08668882825496892,
+      "learning_rate": 1.8542599223254786e-06,
+      "loss": 0.846,
+      "step": 480
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.08475522972496816,
+      "learning_rate": 1.7869033171993575e-06,
+      "loss": 0.8407,
+      "step": 481
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.08771710800870834,
+      "learning_rate": 1.7207552672346471e-06,
+      "loss": 0.8503,
+      "step": 482
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.09111144297342101,
+      "learning_rate": 1.6558186059936587e-06,
+      "loss": 0.8479,
+      "step": 483
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.08620883215580287,
+      "learning_rate": 1.5920961151468327e-06,
+      "loss": 0.8458,
+      "step": 484
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.08471255274938502,
+      "learning_rate": 1.5295905243535847e-06,
+      "loss": 0.8537,
+      "step": 485
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.08449994501906344,
+      "learning_rate": 1.4683045111453942e-06,
+      "loss": 0.8492,
+      "step": 486
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.08739419896581681,
+      "learning_rate": 1.408240700811091e-06,
+      "loss": 0.8524,
+      "step": 487
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.08352102275911637,
+      "learning_rate": 1.3494016662844011e-06,
+      "loss": 0.8476,
+      "step": 488
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.08352827574514726,
+      "learning_rate": 1.2917899280337354e-06,
+      "loss": 0.8551,
+      "step": 489
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.08439329456211196,
+      "learning_rate": 1.2354079539542085e-06,
+      "loss": 0.8416,
+      "step": 490
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.08562104303556034,
+      "learning_rate": 1.1802581592619444e-06,
+      "loss": 0.8501,
+      "step": 491
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.0896431543921245,
+      "learning_rate": 1.126342906390585e-06,
+      "loss": 0.8461,
+      "step": 492
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.08543853113029239,
+      "learning_rate": 1.0736645048901217e-06,
+      "loss": 0.8586,
+      "step": 493
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.08898225127672299,
+      "learning_rate": 1.022225211327954e-06,
+      "loss": 0.846,
+      "step": 494
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.08623358584808383,
+      "learning_rate": 9.720272291922072e-07,
+      "loss": 0.8406,
+      "step": 495
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.08391526822617813,
+      "learning_rate": 9.230727087973712e-07,
+      "loss": 0.8451,
+      "step": 496
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.08567392350575599,
+      "learning_rate": 8.753637471921572e-07,
+      "loss": 0.8408,
+      "step": 497
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.08908923286438868,
+      "learning_rate": 8.289023880697033e-07,
+      "loss": 0.8418,
+      "step": 498
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.08472167209293709,
+      "learning_rate": 7.83690621679991e-07,
+      "loss": 0.8448,
+      "step": 499
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.0841111177111636,
+      "learning_rate": 7.397303847446202e-07,
+      "loss": 0.8482,
+      "step": 500
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.09207138444341484,
+      "learning_rate": 6.970235603738284e-07,
+      "loss": 0.8455,
+      "step": 501
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.08300698846765277,
+      "learning_rate": 6.555719779858294e-07,
+      "loss": 0.8393,
+      "step": 502
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.08410038120955553,
+      "learning_rate": 6.153774132284584e-07,
+      "loss": 0.8426,
+      "step": 503
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.08542102355669302,
+      "learning_rate": 5.764415879030871e-07,
+      "loss": 0.8538,
+      "step": 504
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.08431102358812953,
+      "learning_rate": 5.387661698908852e-07,
+      "loss": 0.8454,
+      "step": 505
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.08201034861685735,
+      "learning_rate": 5.023527730813649e-07,
+      "loss": 0.8492,
+      "step": 506
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.08426514879217514,
+      "learning_rate": 4.672029573032521e-07,
+      "loss": 0.8539,
+      "step": 507
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.08363012777621809,
+      "learning_rate": 4.333182282576675e-07,
+      "loss": 0.8507,
+      "step": 508
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.08403404035574012,
+      "learning_rate": 4.0070003745363073e-07,
+      "loss": 0.8417,
+      "step": 509
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.08556297885057308,
+      "learning_rate": 3.6934978214587026e-07,
+      "loss": 0.8542,
+      "step": 510
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.0830271098839072,
+      "learning_rate": 3.392688052749782e-07,
+      "loss": 0.8384,
+      "step": 511
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.08332845498822317,
+      "learning_rate": 3.1045839540989273e-07,
+      "loss": 0.8497,
+      "step": 512
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.08163756862158367,
+      "learning_rate": 2.829197866926825e-07,
+      "loss": 0.8436,
+      "step": 513
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.08239779756966806,
+      "learning_rate": 2.5665415878568855e-07,
+      "loss": 0.8419,
+      "step": 514
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.0846233275518859,
+      "learning_rate": 2.3166263682098844e-07,
+      "loss": 0.8569,
+      "step": 515
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.08295765011201144,
+      "learning_rate": 2.0794629135221123e-07,
+      "loss": 0.852,
+      "step": 516
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.08898478620134848,
+      "learning_rate": 1.8550613830865758e-07,
+      "loss": 0.8524,
+      "step": 517
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.08253980942709409,
+      "learning_rate": 1.6434313895180132e-07,
+      "loss": 0.8439,
+      "step": 518
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.08658080433487944,
+      "learning_rate": 1.4445819983409546e-07,
+      "loss": 0.8478,
+      "step": 519
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.085494836912567,
+      "learning_rate": 1.2585217276015026e-07,
+      "loss": 0.854,
+      "step": 520
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.08520015820412867,
+      "learning_rate": 1.085258547502388e-07,
+      "loss": 0.8527,
+      "step": 521
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.0835695495145572,
+      "learning_rate": 9.247998800616108e-08,
+      "loss": 0.8514,
+      "step": 522
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.08360415935414345,
+      "learning_rate": 7.771525987944284e-08,
+      "loss": 0.8497,
+      "step": 523
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.0828425664078141,
+      "learning_rate": 6.423230284189563e-08,
+      "loss": 0.8495,
+      "step": 524
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.08252226826743013,
+      "learning_rate": 5.203169445852529e-08,
+      "loss": 0.8412,
+      "step": 525
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.08292638372084292,
+      "learning_rate": 4.1113957362785e-08,
+      "loss": 0.8575,
+      "step": 526
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.08188311347471468,
+      "learning_rate": 3.147955923419654e-08,
+      "loss": 0.841,
+      "step": 527
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.0836376120816663,
+      "learning_rate": 2.3128912778312972e-08,
+      "loss": 0.8484,
+      "step": 528
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.08186296368729573,
+      "learning_rate": 1.6062375709029465e-08,
+      "loss": 0.8544,
+      "step": 529
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.08278337963328566,
+      "learning_rate": 1.0280250733282203e-08,
+      "loss": 0.8478,
+      "step": 530
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.08279493662178963,
+      "learning_rate": 5.7827855380554465e-09,
+      "loss": 0.8465,
+      "step": 531
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.09221939825908573,
+      "learning_rate": 2.570172779789992e-09,
+      "loss": 0.8473,
+      "step": 532
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.09063451115383812,
+      "learning_rate": 6.425500761231274e-10,
+      "loss": 0.8581,
+      "step": 533
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.08387090563875321,
+      "learning_rate": 0.0,
+      "loss": 0.8385,
+      "step": 534
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8818458318710327,
+      "eval_runtime": 352.6305,
+      "eval_samples_per_second": 37.135,
+      "eval_steps_per_second": 0.057,
+      "step": 534
+    },
+    {
+      "epoch": 3.0,
+      "step": 534,
+      "total_flos": 4217873142644736.0,
+      "train_loss": 0.9222131907270196,
+      "train_runtime": 33956.1835,
+      "train_samples_per_second": 10.545,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 534,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 4217873142644736.0,
+  "train_batch_size": 42,
+  "trial_name": null,
+  "trial_params": null
+}