Model save

README.md

@@ -0,0 +1,69 @@
+---
+license: llama2
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: llama2-7b-sft-full-zephyr
+  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. -->
+
+# llama2-7b-sft-full-zephyr
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0288
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9861        | 0.9971 | 127  | 1.0089          |
+| 0.8393        | 1.9941 | 254  | 0.9976          |
+| 0.7166        | 2.9912 | 381  | 1.0288          |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9911678115799805,
+    "total_flos": 159494952714240.0,
+    "train_loss": 0.9007005614871428,
+    "train_runtime": 67911.5352,
+    "train_samples": 61134,
+    "train_samples_per_second": 0.72,
+    "train_steps_per_second": 0.006
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa909bde2ee8f8168ae3022613b4813170ad33bad1b837a6015bc6199fcd411e
+size 4840396416

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f39c9504bb73e94e555e1b56049686d2eb684a88b582fc97899991e6c9bcfbb
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38cb82086d2746ee7376b90e176191d9914371f7733dbf29603136ce6e9aceea
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3302079a7c256d4777da28505bc686f8b0a1e5e47283ee63d54e6ad5451e9de6
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a89154f185bdc21775620aaee749b018d4ef77c1a6b80d8ee6fb41f30d4733
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de72e943903103cf5ee7278e331b0f56bcebcc85316c0c51cdce84881cd045c
+size 2684472112

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953662464
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9911678115799805,
+    "total_flos": 159494952714240.0,
+    "train_loss": 0.9007005614871428,
+    "train_runtime": 67911.5352,
+    "train_samples": 61134,
+    "train_samples_per_second": 0.72,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,2733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9911678115799805,
+  "eval_steps": 500,
+  "global_step": 381,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007850834151128557,
+      "grad_norm": 7.347224534644921,
+      "learning_rate": 5.128205128205128e-07,
+      "loss": 1.6659,
+      "step": 1
+    },
+    {
+      "epoch": 0.015701668302257114,
+      "grad_norm": 6.800736485391032,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 1.6461,
+      "step": 2
+    },
+    {
+      "epoch": 0.023552502453385672,
+      "grad_norm": 6.120850052409094,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 1.6139,
+      "step": 3
+    },
+    {
+      "epoch": 0.03140333660451423,
+      "grad_norm": 4.906337313138213,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 1.5437,
+      "step": 4
+    },
+    {
+      "epoch": 0.03925417075564279,
+      "grad_norm": 4.455076188041479,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 1.5144,
+      "step": 5
+    },
+    {
+      "epoch": 0.047105004906771344,
+      "grad_norm": 3.6233673156984016,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 1.451,
+      "step": 6
+    },
+    {
+      "epoch": 0.0549558390578999,
+      "grad_norm": 2.925023291585002,
+      "learning_rate": 3.58974358974359e-06,
+      "loss": 1.3415,
+      "step": 7
+    },
+    {
+      "epoch": 0.06280667320902845,
+      "grad_norm": 3.491464855206146,
+      "learning_rate": 4.102564102564103e-06,
+      "loss": 1.2789,
+      "step": 8
+    },
+    {
+      "epoch": 0.07065750736015702,
+      "grad_norm": 2.614590714072604,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 1.2611,
+      "step": 9
+    },
+    {
+      "epoch": 0.07850834151128558,
+      "grad_norm": 2.4520189198230344,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 1.2584,
+      "step": 10
+    },
+    {
+      "epoch": 0.08635917566241413,
+      "grad_norm": 2.9131892725083097,
+      "learning_rate": 5.641025641025641e-06,
+      "loss": 1.2471,
+      "step": 11
+    },
+    {
+      "epoch": 0.09421000981354269,
+      "grad_norm": 1.7656207299437792,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 1.2413,
+      "step": 12
+    },
+    {
+      "epoch": 0.10206084396467124,
+      "grad_norm": 1.2787313629514108,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.2016,
+      "step": 13
+    },
+    {
+      "epoch": 0.1099116781157998,
+      "grad_norm": 0.9994635257798418,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 1.1953,
+      "step": 14
+    },
+    {
+      "epoch": 0.11776251226692837,
+      "grad_norm": 0.9070553314758185,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.1997,
+      "step": 15
+    },
+    {
+      "epoch": 0.1256133464180569,
+      "grad_norm": 1.064553340997491,
+      "learning_rate": 8.205128205128205e-06,
+      "loss": 1.2066,
+      "step": 16
+    },
+    {
+      "epoch": 0.13346418056918546,
+      "grad_norm": 0.6960157702047296,
+      "learning_rate": 8.717948717948719e-06,
+      "loss": 1.1986,
+      "step": 17
+    },
+    {
+      "epoch": 0.14131501472031405,
+      "grad_norm": 0.713190737451088,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 1.1818,
+      "step": 18
+    },
+    {
+      "epoch": 0.1491658488714426,
+      "grad_norm": 0.5606304883153309,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 1.1727,
+      "step": 19
+    },
+    {
+      "epoch": 0.15701668302257116,
+      "grad_norm": 0.7333593290821419,
+      "learning_rate": 1.0256410256410256e-05,
+      "loss": 1.187,
+      "step": 20
+    },
+    {
+      "epoch": 0.1648675171736997,
+      "grad_norm": 0.5177096471120355,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 1.1503,
+      "step": 21
+    },
+    {
+      "epoch": 0.17271835132482827,
+      "grad_norm": 0.489041421135395,
+      "learning_rate": 1.1282051282051283e-05,
+      "loss": 1.1192,
+      "step": 22
+    },
+    {
+      "epoch": 0.18056918547595682,
+      "grad_norm": 1.3968342819533879,
+      "learning_rate": 1.1794871794871796e-05,
+      "loss": 1.1862,
+      "step": 23
+    },
+    {
+      "epoch": 0.18842001962708538,
+      "grad_norm": 0.5508740207033395,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 1.1656,
+      "step": 24
+    },
+    {
+      "epoch": 0.19627085377821393,
+      "grad_norm": 0.4986756374114125,
+      "learning_rate": 1.2820512820512823e-05,
+      "loss": 1.1328,
+      "step": 25
+    },
+    {
+      "epoch": 0.2041216879293425,
+      "grad_norm": 0.5005164618815391,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1057,
+      "step": 26
+    },
+    {
+      "epoch": 0.21197252208047104,
+      "grad_norm": 0.45494783925644244,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 1.1168,
+      "step": 27
+    },
+    {
+      "epoch": 0.2198233562315996,
+      "grad_norm": 0.6579318599501837,
+      "learning_rate": 1.435897435897436e-05,
+      "loss": 1.1496,
+      "step": 28
+    },
+    {
+      "epoch": 0.22767419038272815,
+      "grad_norm": 0.44794686872085726,
+      "learning_rate": 1.4871794871794874e-05,
+      "loss": 1.1251,
+      "step": 29
+    },
+    {
+      "epoch": 0.23552502453385674,
+      "grad_norm": 0.46768599260305055,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.1215,
+      "step": 30
+    },
+    {
+      "epoch": 0.2433758586849853,
+      "grad_norm": 0.39441965866938333,
+      "learning_rate": 1.5897435897435897e-05,
+      "loss": 1.0904,
+      "step": 31
+    },
+    {
+      "epoch": 0.2512266928361138,
+      "grad_norm": 0.43438585512410144,
+      "learning_rate": 1.641025641025641e-05,
+      "loss": 1.134,
+      "step": 32
+    },
+    {
+      "epoch": 0.2590775269872424,
+      "grad_norm": 0.3976733272593362,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 1.1373,
+      "step": 33
+    },
+    {
+      "epoch": 0.26692836113837093,
+      "grad_norm": 0.43273997287228855,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 1.1244,
+      "step": 34
+    },
+    {
+      "epoch": 0.2747791952894995,
+      "grad_norm": 0.39215827450277185,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 1.1105,
+      "step": 35
+    },
+    {
+      "epoch": 0.2826300294406281,
+      "grad_norm": 0.4227406449692189,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 1.0914,
+      "step": 36
+    },
+    {
+      "epoch": 0.2904808635917566,
+      "grad_norm": 0.4087861429403669,
+      "learning_rate": 1.8974358974358975e-05,
+      "loss": 1.0902,
+      "step": 37
+    },
+    {
+      "epoch": 0.2983316977428852,
+      "grad_norm": 0.431394664105538,
+      "learning_rate": 1.9487179487179488e-05,
+      "loss": 1.116,
+      "step": 38
+    },
+    {
+      "epoch": 0.30618253189401373,
+      "grad_norm": 0.41278733736546896,
+      "learning_rate": 2e-05,
+      "loss": 1.0902,
+      "step": 39
+    },
+    {
+      "epoch": 0.3140333660451423,
+      "grad_norm": 0.44066943149034954,
+      "learning_rate": 1.9999578095183126e-05,
+      "loss": 1.1263,
+      "step": 40
+    },
+    {
+      "epoch": 0.32188420019627084,
+      "grad_norm": 0.4176620676156422,
+      "learning_rate": 1.999831241633323e-05,
+      "loss": 1.0736,
+      "step": 41
+    },
+    {
+      "epoch": 0.3297350343473994,
+      "grad_norm": 0.43233210528814153,
+      "learning_rate": 1.9996203070249516e-05,
+      "loss": 1.0897,
+      "step": 42
+    },
+    {
+      "epoch": 0.33758586849852795,
+      "grad_norm": 0.47859464887906467,
+      "learning_rate": 1.9993250234920638e-05,
+      "loss": 1.1021,
+      "step": 43
+    },
+    {
+      "epoch": 0.34543670264965654,
+      "grad_norm": 0.4258761642972358,
+      "learning_rate": 1.998945415950969e-05,
+      "loss": 1.1077,
+      "step": 44
+    },
+    {
+      "epoch": 0.35328753680078506,
+      "grad_norm": 0.4284792897069604,
+      "learning_rate": 1.9984815164333163e-05,
+      "loss": 1.0803,
+      "step": 45
+    },
+    {
+      "epoch": 0.36113837095191365,
+      "grad_norm": 0.3907300716721876,
+      "learning_rate": 1.9979333640833947e-05,
+      "loss": 1.1113,
+      "step": 46
+    },
+    {
+      "epoch": 0.3689892051030422,
+      "grad_norm": 0.45186935418198326,
+      "learning_rate": 1.9973010051548274e-05,
+      "loss": 1.0812,
+      "step": 47
+    },
+    {
+      "epoch": 0.37684003925417076,
+      "grad_norm": 0.38125071489505413,
+      "learning_rate": 1.99658449300667e-05,
+      "loss": 1.0754,
+      "step": 48
+    },
+    {
+      "epoch": 0.38469087340529934,
+      "grad_norm": 0.45080107205590203,
+      "learning_rate": 1.9957838880989076e-05,
+      "loss": 1.0841,
+      "step": 49
+    },
+    {
+      "epoch": 0.39254170755642787,
+      "grad_norm": 0.3989024345777725,
+      "learning_rate": 1.9948992579873538e-05,
+      "loss": 1.0735,
+      "step": 50
+    },
+    {
+      "epoch": 0.40039254170755645,
+      "grad_norm": 0.5091781669676405,
+      "learning_rate": 1.9939306773179498e-05,
+      "loss": 1.0379,
+      "step": 51
+    },
+    {
+      "epoch": 0.408243375858685,
+      "grad_norm": 0.39302600440038105,
+      "learning_rate": 1.992878227820465e-05,
+      "loss": 1.0801,
+      "step": 52
+    },
+    {
+      "epoch": 0.41609421000981356,
+      "grad_norm": 0.4747065341629128,
+      "learning_rate": 1.9917419983016025e-05,
+      "loss": 1.0738,
+      "step": 53
+    },
+    {
+      "epoch": 0.4239450441609421,
+      "grad_norm": 0.3901535523861331,
+      "learning_rate": 1.990522084637503e-05,
+      "loss": 1.0886,
+      "step": 54
+    },
+    {
+      "epoch": 0.43179587831207067,
+      "grad_norm": 0.5806279931199742,
+      "learning_rate": 1.989218589765658e-05,
+      "loss": 1.0654,
+      "step": 55
+    },
+    {
+      "epoch": 0.4396467124631992,
+      "grad_norm": 0.43170153156662455,
+      "learning_rate": 1.9878316236762195e-05,
+      "loss": 1.0904,
+      "step": 56
+    },
+    {
+      "epoch": 0.4474975466143278,
+      "grad_norm": 0.4731072250955362,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 1.082,
+      "step": 57
+    },
+    {
+      "epoch": 0.4553483807654563,
+      "grad_norm": 2.445941073324572,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 1.0743,
+      "step": 58
+    },
+    {
+      "epoch": 0.4631992149165849,
+      "grad_norm": 0.5477954510879893,
+      "learning_rate": 1.9831711035947552e-05,
+      "loss": 1.0177,
+      "step": 59
+    },
+    {
+      "epoch": 0.47105004906771347,
+      "grad_norm": 0.4298809448303284,
+      "learning_rate": 1.981451493252418e-05,
+      "loss": 1.0846,
+      "step": 60
+    },
+    {
+      "epoch": 0.478900883218842,
+      "grad_norm": 0.5166668485586924,
+      "learning_rate": 1.979649067087574e-05,
+      "loss": 1.0562,
+      "step": 61
+    },
+    {
+      "epoch": 0.4867517173699706,
+      "grad_norm": 0.4167975268273255,
+      "learning_rate": 1.9777639771906795e-05,
+      "loss": 1.023,
+      "step": 62
+    },
+    {
+      "epoch": 0.4946025515210991,
+      "grad_norm": 0.5715335893900569,
+      "learning_rate": 1.9757963826274357e-05,
+      "loss": 1.0604,
+      "step": 63
+    },
+    {
+      "epoch": 0.5024533856722276,
+      "grad_norm": 0.3961190441597043,
+      "learning_rate": 1.973746449425368e-05,
+      "loss": 1.0221,
+      "step": 64
+    },
+    {
+      "epoch": 0.5103042198233563,
+      "grad_norm": 0.48220393643694165,
+      "learning_rate": 1.971614350559814e-05,
+      "loss": 1.0669,
+      "step": 65
+    },
+    {
+      "epoch": 0.5181550539744848,
+      "grad_norm": 0.4209271371207164,
+      "learning_rate": 1.9694002659393306e-05,
+      "loss": 1.0523,
+      "step": 66
+    },
+    {
+      "epoch": 0.5260058881256133,
+      "grad_norm": 0.5080029927537019,
+      "learning_rate": 1.967104382390511e-05,
+      "loss": 1.0657,
+      "step": 67
+    },
+    {
+      "epoch": 0.5338567222767419,
+      "grad_norm": 0.4139294104561131,
+      "learning_rate": 1.9647268936422204e-05,
+      "loss": 1.0571,
+      "step": 68
+    },
+    {
+      "epoch": 0.5417075564278705,
+      "grad_norm": 0.47336391741191297,
+      "learning_rate": 1.9622680003092503e-05,
+      "loss": 1.065,
+      "step": 69
+    },
+    {
+      "epoch": 0.549558390578999,
+      "grad_norm": 0.4599155655835422,
+      "learning_rate": 1.9597279098753893e-05,
+      "loss": 1.0707,
+      "step": 70
+    },
+    {
+      "epoch": 0.5574092247301276,
+      "grad_norm": 0.42721814520105705,
+      "learning_rate": 1.9571068366759143e-05,
+      "loss": 1.0201,
+      "step": 71
+    },
+    {
+      "epoch": 0.5652600588812562,
+      "grad_norm": 0.4789530282992036,
+      "learning_rate": 1.9544050018795076e-05,
+      "loss": 1.0339,
+      "step": 72
+    },
+    {
+      "epoch": 0.5731108930323847,
+      "grad_norm": 0.38399215622832134,
+      "learning_rate": 1.951622633469592e-05,
+      "loss": 1.0503,
+      "step": 73
+    },
+    {
+      "epoch": 0.5809617271835132,
+      "grad_norm": 0.5309252502685154,
+      "learning_rate": 1.9487599662250945e-05,
+      "loss": 1.0325,
+      "step": 74
+    },
+    {
+      "epoch": 0.5888125613346418,
+      "grad_norm": 0.3873622740594628,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 1.0352,
+      "step": 75
+    },
+    {
+      "epoch": 0.5966633954857704,
+      "grad_norm": 0.4650308612508396,
+      "learning_rate": 1.9427947082061432e-05,
+      "loss": 1.0514,
+      "step": 76
+    },
+    {
+      "epoch": 0.6045142296368989,
+      "grad_norm": 0.41421148432519594,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.0423,
+      "step": 77
+    },
+    {
+      "epoch": 0.6123650637880275,
+      "grad_norm": 0.4200729762455513,
+      "learning_rate": 1.936511241197055e-05,
+      "loss": 1.0261,
+      "step": 78
+    },
+    {
+      "epoch": 0.620215897939156,
+      "grad_norm": 0.439339283275543,
+      "learning_rate": 1.933250837887457e-05,
+      "loss": 1.0716,
+      "step": 79
+    },
+    {
+      "epoch": 0.6280667320902846,
+      "grad_norm": 0.39239965168183033,
+      "learning_rate": 1.929911685973088e-05,
+      "loss": 1.0279,
+      "step": 80
+    },
+    {
+      "epoch": 0.6359175662414132,
+      "grad_norm": 0.43943297124679154,
+      "learning_rate": 1.9264940672148018e-05,
+      "loss": 1.0339,
+      "step": 81
+    },
+    {
+      "epoch": 0.6437684003925417,
+      "grad_norm": 0.3823350992771719,
+      "learning_rate": 1.922998269994563e-05,
+      "loss": 1.0405,
+      "step": 82
+    },
+    {
+      "epoch": 0.6516192345436702,
+      "grad_norm": 0.4383434308159265,
+      "learning_rate": 1.9194245892911077e-05,
+      "loss": 1.0642,
+      "step": 83
+    },
+    {
+      "epoch": 0.6594700686947988,
+      "grad_norm": 0.3856705013763455,
+      "learning_rate": 1.9157733266550577e-05,
+      "loss": 1.057,
+      "step": 84
+    },
+    {
+      "epoch": 0.6673209028459274,
+      "grad_norm": 0.45820906953276863,
+      "learning_rate": 1.9120447901834708e-05,
+      "loss": 1.0399,
+      "step": 85
+    },
+    {
+      "epoch": 0.6751717369970559,
+      "grad_norm": 0.3770988817991561,
+      "learning_rate": 1.9082392944938467e-05,
+      "loss": 1.0128,
+      "step": 86
+    },
+    {
+      "epoch": 0.6830225711481845,
+      "grad_norm": 0.3886490118801202,
+      "learning_rate": 1.9043571606975776e-05,
+      "loss": 1.0427,
+      "step": 87
+    },
+    {
+      "epoch": 0.6908734052993131,
+      "grad_norm": 0.38404685198757366,
+      "learning_rate": 1.9003987163728535e-05,
+      "loss": 1.0468,
+      "step": 88
+    },
+    {
+      "epoch": 0.6987242394504416,
+      "grad_norm": 0.3856126315988586,
+      "learning_rate": 1.8963642955370203e-05,
+      "loss": 1.0188,
+      "step": 89
+    },
+    {
+      "epoch": 0.7065750736015701,
+      "grad_norm": 0.39691940499911565,
+      "learning_rate": 1.8922542386183942e-05,
+      "loss": 1.0431,
+      "step": 90
+    },
+    {
+      "epoch": 0.7144259077526988,
+      "grad_norm": 0.37646713546648325,
+      "learning_rate": 1.888068892427538e-05,
+      "loss": 1.0123,
+      "step": 91
+    },
+    {
+      "epoch": 0.7222767419038273,
+      "grad_norm": 0.38202063303210265,
+      "learning_rate": 1.8838086101279946e-05,
+      "loss": 0.9795,
+      "step": 92
+    },
+    {
+      "epoch": 0.7301275760549558,
+      "grad_norm": 0.4006436007553303,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 1.0406,
+      "step": 93
+    },
+    {
+      "epoch": 0.7379784102060843,
+      "grad_norm": 0.40042604218912303,
+      "learning_rate": 1.875064681442594e-05,
+      "loss": 1.0374,
+      "step": 94
+    },
+    {
+      "epoch": 0.745829244357213,
+      "grad_norm": 0.3661500415244952,
+      "learning_rate": 1.8705817728778626e-05,
+      "loss": 0.9875,
+      "step": 95
+    },
+    {
+      "epoch": 0.7536800785083415,
+      "grad_norm": 0.5321046827534726,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.9967,
+      "step": 96
+    },
+    {
+      "epoch": 0.76153091265947,
+      "grad_norm": 0.380675610761362,
+      "learning_rate": 1.8613959586331364e-05,
+      "loss": 1.0461,
+      "step": 97
+    },
+    {
+      "epoch": 0.7693817468105987,
+      "grad_norm": 0.4024806550045475,
+      "learning_rate": 1.8566938280609965e-05,
+      "loss": 1.0099,
+      "step": 98
+    },
+    {
+      "epoch": 0.7772325809617272,
+      "grad_norm": 0.370814638092088,
+      "learning_rate": 1.851919408838327e-05,
+      "loss": 1.0207,
+      "step": 99
+    },
+    {
+      "epoch": 0.7850834151128557,
+      "grad_norm": 0.3806524412935442,
+      "learning_rate": 1.847073103835222e-05,
+      "loss": 1.0159,
+      "step": 100
+    },
+    {
+      "epoch": 0.7929342492639843,
+      "grad_norm": 0.4108674800403207,
+      "learning_rate": 1.842155321987566e-05,
+      "loss": 1.0778,
+      "step": 101
+    },
+    {
+      "epoch": 0.8007850834151129,
+      "grad_norm": 0.37403031988868396,
+      "learning_rate": 1.8371664782625287e-05,
+      "loss": 1.0332,
+      "step": 102
+    },
+    {
+      "epoch": 0.8086359175662414,
+      "grad_norm": 0.3836349453115177,
+      "learning_rate": 1.8321069936235503e-05,
+      "loss": 1.0215,
+      "step": 103
+    },
+    {
+      "epoch": 0.81648675171737,
+      "grad_norm": 0.37875125110678953,
+      "learning_rate": 1.8269772949948185e-05,
+      "loss": 1.0247,
+      "step": 104
+    },
+    {
+      "epoch": 0.8243375858684985,
+      "grad_norm": 0.3784814549707884,
+      "learning_rate": 1.821777815225245e-05,
+      "loss": 1.0078,
+      "step": 105
+    },
+    {
+      "epoch": 0.8321884200196271,
+      "grad_norm": 0.3822474296598352,
+      "learning_rate": 1.816508993051943e-05,
+      "loss": 1.0252,
+      "step": 106
+    },
+    {
+      "epoch": 0.8400392541707556,
+      "grad_norm": 0.3822473221882239,
+      "learning_rate": 1.8111712730632024e-05,
+      "loss": 1.0211,
+      "step": 107
+    },
+    {
+      "epoch": 0.8478900883218842,
+      "grad_norm": 0.3962833061232879,
+      "learning_rate": 1.8057651056609784e-05,
+      "loss": 1.0037,
+      "step": 108
+    },
+    {
+      "epoch": 0.8557409224730128,
+      "grad_norm": 0.3781060741624514,
+      "learning_rate": 1.800290947022884e-05,
+      "loss": 1.0012,
+      "step": 109
+    },
+    {
+      "epoch": 0.8635917566241413,
+      "grad_norm": 0.3865238595691672,
+      "learning_rate": 1.7947492590636998e-05,
+      "loss": 0.9966,
+      "step": 110
+    },
+    {
+      "epoch": 0.8714425907752699,
+      "grad_norm": 0.3732505111156178,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 1.0572,
+      "step": 111
+    },
+    {
+      "epoch": 0.8792934249263984,
+      "grad_norm": 0.37554006668798495,
+      "learning_rate": 1.7834651712926662e-05,
+      "loss": 1.0009,
+      "step": 112
+    },
+    {
+      "epoch": 0.887144259077527,
+      "grad_norm": 0.3839292026543955,
+      "learning_rate": 1.777723723643014e-05,
+      "loss": 1.0142,
+      "step": 113
+    },
+    {
+      "epoch": 0.8949950932286556,
+      "grad_norm": 0.3892163416918322,
+      "learning_rate": 1.771916650916321e-05,
+      "loss": 1.016,
+      "step": 114
+    },
+    {
+      "epoch": 0.9028459273797841,
+      "grad_norm": 0.38311302328482383,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.0091,
+      "step": 115
+    },
+    {
+      "epoch": 0.9106967615309126,
+      "grad_norm": 0.38806483820436577,
+      "learning_rate": 1.7601075957535366e-05,
+      "loss": 1.0189,
+      "step": 116
+    },
+    {
+      "epoch": 0.9185475956820413,
+      "grad_norm": 0.3931144378224063,
+      "learning_rate": 1.7541066097768965e-05,
+      "loss": 0.9923,
+      "step": 117
+    },
+    {
+      "epoch": 0.9263984298331698,
+      "grad_norm": 0.36480472960450744,
+      "learning_rate": 1.7480419915580357e-05,
+      "loss": 0.9729,
+      "step": 118
+    },
+    {
+      "epoch": 0.9342492639842983,
+      "grad_norm": 0.3959807593506061,
+      "learning_rate": 1.7419142528352815e-05,
+      "loss": 1.0103,
+      "step": 119
+    },
+    {
+      "epoch": 0.9421000981354269,
+      "grad_norm": 0.37926932457436413,
+      "learning_rate": 1.735723910673132e-05,
+      "loss": 1.0078,
+      "step": 120
+    },
+    {
+      "epoch": 0.9499509322865555,
+      "grad_norm": 0.3943417649387235,
+      "learning_rate": 1.729471487418621e-05,
+      "loss": 1.0062,
+      "step": 121
+    },
+    {
+      "epoch": 0.957801766437684,
+      "grad_norm": 0.40856232664967546,
+      "learning_rate": 1.723157510657247e-05,
+      "loss": 0.9602,
+      "step": 122
+    },
+    {
+      "epoch": 0.9656526005888125,
+      "grad_norm": 0.40120567592768724,
+      "learning_rate": 1.7167825131684516e-05,
+      "loss": 1.0472,
+      "step": 123
+    },
+    {
+      "epoch": 0.9735034347399412,
+      "grad_norm": 0.40515597429363565,
+      "learning_rate": 1.710347032880664e-05,
+      "loss": 1.0279,
+      "step": 124
+    },
+    {
+      "epoch": 0.9813542688910697,
+      "grad_norm": 0.39649247036981716,
+      "learning_rate": 1.7038516128259118e-05,
+      "loss": 1.0431,
+      "step": 125
+    },
+    {
+      "epoch": 0.9892051030421982,
+      "grad_norm": 0.3789017397674644,
+      "learning_rate": 1.6972968010939953e-05,
+      "loss": 1.0133,
+      "step": 126
+    },
+    {
+      "epoch": 0.9970559371933267,
+      "grad_norm": 0.39808368574851577,
+      "learning_rate": 1.6906831507862446e-05,
+      "loss": 0.9861,
+      "step": 127
+    },
+    {
+      "epoch": 0.9970559371933267,
+      "eval_loss": 1.008862853050232,
+      "eval_runtime": 87.6937,
+      "eval_samples_per_second": 3.067,
+      "eval_steps_per_second": 0.194,
+      "step": 127
+    },
+    {
+      "epoch": 1.0049067713444553,
+      "grad_norm": 0.5650249011874021,
+      "learning_rate": 1.6840112199688432e-05,
+      "loss": 0.9219,
+      "step": 128
+    },
+    {
+      "epoch": 1.0127576054955838,
+      "grad_norm": 0.5128582783019816,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.9049,
+      "step": 129
+    },
+    {
+      "epoch": 1.0206084396467126,
+      "grad_norm": 0.5753637983633895,
+      "learning_rate": 1.670494773611149e-05,
+      "loss": 0.8689,
+      "step": 130
+    },
+    {
+      "epoch": 1.028459273797841,
+      "grad_norm": 0.48975845202045304,
+      "learning_rate": 1.6636513986016215e-05,
+      "loss": 0.8566,
+      "step": 131
+    },
+    {
+      "epoch": 1.0363101079489696,
+      "grad_norm": 0.5791649314164773,
+      "learning_rate": 1.6567520240477344e-05,
+      "loss": 0.878,
+      "step": 132
+    },
+    {
+      "epoch": 1.0441609421000981,
+      "grad_norm": 0.4594130089791179,
+      "learning_rate": 1.64979723212536e-05,
+      "loss": 0.8979,
+      "step": 133
+    },
+    {
+      "epoch": 1.0520117762512267,
+      "grad_norm": 0.43514374553184754,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.8697,
+      "step": 134
+    },
+    {
+      "epoch": 1.0598626104023552,
+      "grad_norm": 0.4519110504501915,
+      "learning_rate": 1.6357237482099682e-05,
+      "loss": 0.8893,
+      "step": 135
+    },
+    {
+      "epoch": 1.0677134445534837,
+      "grad_norm": 0.43411209136548795,
+      "learning_rate": 1.6286062437510823e-05,
+      "loss": 0.8597,
+      "step": 136
+    },
+    {
+      "epoch": 1.0755642787046125,
+      "grad_norm": 0.4387204236074357,
+      "learning_rate": 1.621435696891765e-05,
+      "loss": 0.8753,
+      "step": 137
+    },
+    {
+      "epoch": 1.083415112855741,
+      "grad_norm": 0.43981422151940164,
+      "learning_rate": 1.6142127126896682e-05,
+      "loss": 0.849,
+      "step": 138
+    },
+    {
+      "epoch": 1.0912659470068695,
+      "grad_norm": 0.5001339131218675,
+      "learning_rate": 1.606937900627157e-05,
+      "loss": 0.8886,
+      "step": 139
+    },
+    {
+      "epoch": 1.099116781157998,
+      "grad_norm": 0.3962962559222613,
+      "learning_rate": 1.5996118745598817e-05,
+      "loss": 0.8984,
+      "step": 140
+    },
+    {
+      "epoch": 1.1069676153091266,
+      "grad_norm": 0.410837879553188,
+      "learning_rate": 1.5922352526649803e-05,
+      "loss": 0.8702,
+      "step": 141
+    },
+    {
+      "epoch": 1.114818449460255,
+      "grad_norm": 0.3900972440526185,
+      "learning_rate": 1.584808657388914e-05,
+      "loss": 0.857,
+      "step": 142
+    },
+    {
+      "epoch": 1.1226692836113836,
+      "grad_norm": 0.50050898812635,
+      "learning_rate": 1.5773327153949465e-05,
+      "loss": 0.8564,
+      "step": 143
+    },
+    {
+      "epoch": 1.1305201177625124,
+      "grad_norm": 0.42276658241059106,
+      "learning_rate": 1.5698080575102662e-05,
+      "loss": 0.8731,
+      "step": 144
+    },
+    {
+      "epoch": 1.138370951913641,
+      "grad_norm": 0.3904125438204647,
+      "learning_rate": 1.5622353186727542e-05,
+      "loss": 0.8677,
+      "step": 145
+    },
+    {
+      "epoch": 1.1462217860647694,
+      "grad_norm": 0.39173996458179683,
+      "learning_rate": 1.554615137877409e-05,
+      "loss": 0.8734,
+      "step": 146
+    },
+    {
+      "epoch": 1.154072620215898,
+      "grad_norm": 0.3872952791021188,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.8568,
+      "step": 147
+    },
+    {
+      "epoch": 1.1619234543670265,
+      "grad_norm": 0.4371218247896631,
+      "learning_rate": 1.5392350263549462e-05,
+      "loss": 0.877,
+      "step": 148
+    },
+    {
+      "epoch": 1.169774288518155,
+      "grad_norm": 0.3831001117034703,
+      "learning_rate": 1.531476393416456e-05,
+      "loss": 0.8389,
+      "step": 149
+    },
+    {
+      "epoch": 1.1776251226692835,
+      "grad_norm": 0.4103327638914055,
+      "learning_rate": 1.523672913987878e-05,
+      "loss": 0.8645,
+      "step": 150
+    },
+    {
+      "epoch": 1.185475956820412,
+      "grad_norm": 0.3903171931160864,
+      "learning_rate": 1.5158252465343242e-05,
+      "loss": 0.8731,
+      "step": 151
+    },
+    {
+      "epoch": 1.1933267909715408,
+      "grad_norm": 0.39642256833068346,
+      "learning_rate": 1.5079340532495344e-05,
+      "loss": 0.8721,
+      "step": 152
+    },
+    {
+      "epoch": 1.2011776251226693,
+      "grad_norm": 0.4145883498441255,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8791,
+      "step": 153
+    },
+    {
+      "epoch": 1.2090284592737979,
+      "grad_norm": 0.37776843862430537,
+      "learning_rate": 1.4920237562687784e-05,
+      "loss": 0.8511,
+      "step": 154
+    },
+    {
+      "epoch": 1.2168792934249264,
+      "grad_norm": 0.38611124319994095,
+      "learning_rate": 1.4840059950989992e-05,
+      "loss": 0.912,
+      "step": 155
+    },
+    {
+      "epoch": 1.224730127576055,
+      "grad_norm": 0.40202851943138307,
+      "learning_rate": 1.4759473930370738e-05,
+      "loss": 0.8741,
+      "step": 156
+    },
+    {
+      "epoch": 1.2325809617271835,
+      "grad_norm": 0.4077686105654449,
+      "learning_rate": 1.467848630075608e-05,
+      "loss": 0.8326,
+      "step": 157
+    },
+    {
+      "epoch": 1.240431795878312,
+      "grad_norm": 0.4189626612094213,
+      "learning_rate": 1.4597103895960228e-05,
+      "loss": 0.8919,
+      "step": 158
+    },
+    {
+      "epoch": 1.2482826300294407,
+      "grad_norm": 0.43751276309379905,
+      "learning_rate": 1.4515333583108896e-05,
+      "loss": 0.8917,
+      "step": 159
+    },
+    {
+      "epoch": 1.2561334641805693,
+      "grad_norm": 0.4431204902312222,
+      "learning_rate": 1.4433182262059861e-05,
+      "loss": 0.8631,
+      "step": 160
+    },
+    {
+      "epoch": 1.2639842983316978,
+      "grad_norm": 0.45766691497470235,
+      "learning_rate": 1.4350656864820733e-05,
+      "loss": 0.9106,
+      "step": 161
+    },
+    {
+      "epoch": 1.2718351324828263,
+      "grad_norm": 0.5031570979005162,
+      "learning_rate": 1.4267764354964038e-05,
+      "loss": 0.8697,
+      "step": 162
+    },
+    {
+      "epoch": 1.2796859666339548,
+      "grad_norm": 0.39648971229361624,
+      "learning_rate": 1.4184511727039612e-05,
+      "loss": 0.8538,
+      "step": 163
+    },
+    {
+      "epoch": 1.2875368007850834,
+      "grad_norm": 0.46232891456268915,
+      "learning_rate": 1.4100906005984404e-05,
+      "loss": 0.8616,
+      "step": 164
+    },
+    {
+      "epoch": 1.295387634936212,
+      "grad_norm": 4.350194084370937,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.9134,
+      "step": 165
+    },
+    {
+      "epoch": 1.3032384690873404,
+      "grad_norm": 0.4702977680921452,
+      "learning_rate": 1.3932663532605832e-05,
+      "loss": 0.8651,
+      "step": 166
+    },
+    {
+      "epoch": 1.311089303238469,
+      "grad_norm": 0.4343366395321563,
+      "learning_rate": 1.3848040976744459e-05,
+      "loss": 0.8684,
+      "step": 167
+    },
+    {
+      "epoch": 1.3189401373895977,
+      "grad_norm": 0.43351129788344345,
+      "learning_rate": 1.3763093719478357e-05,
+      "loss": 0.8668,
+      "step": 168
+    },
+    {
+      "epoch": 1.3267909715407262,
+      "grad_norm": 0.4540450822122525,
+      "learning_rate": 1.3677828928738934e-05,
+      "loss": 0.8879,
+      "step": 169
+    },
+    {
+      "epoch": 1.3346418056918548,
+      "grad_norm": 0.39253267361162714,
+      "learning_rate": 1.3592253799251377e-05,
+      "loss": 0.8401,
+      "step": 170
+    },
+    {
+      "epoch": 1.3424926398429833,
+      "grad_norm": 0.4288413337095054,
+      "learning_rate": 1.3506375551927546e-05,
+      "loss": 0.874,
+      "step": 171
+    },
+    {
+      "epoch": 1.3503434739941118,
+      "grad_norm": 0.4168731920075532,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.8795,
+      "step": 172
+    },
+    {
+      "epoch": 1.3581943081452406,
+      "grad_norm": 0.40213666566379325,
+      "learning_rate": 1.3333738714693958e-05,
+      "loss": 0.8602,
+      "step": 173
+    },
+    {
+      "epoch": 1.366045142296369,
+      "grad_norm": 0.45498199146611623,
+      "learning_rate": 1.3246994692046837e-05,
+      "loss": 0.8578,
+      "step": 174
+    },
+    {
+      "epoch": 1.3738959764474976,
+      "grad_norm": 0.3875649087842161,
+      "learning_rate": 1.3159976684859528e-05,
+      "loss": 0.8321,
+      "step": 175
+    },
+    {
+      "epoch": 1.3817468105986261,
+      "grad_norm": 0.48717934285240294,
+      "learning_rate": 1.3072692035795305e-05,
+      "loss": 0.8906,
+      "step": 176
+    },
+    {
+      "epoch": 1.3895976447497547,
+      "grad_norm": 0.41810412667961094,
+      "learning_rate": 1.2985148110016947e-05,
+      "loss": 0.8535,
+      "step": 177
+    },
+    {
+      "epoch": 1.3974484789008832,
+      "grad_norm": 0.47450825597039714,
+      "learning_rate": 1.2897352294565248e-05,
+      "loss": 0.8621,
+      "step": 178
+    },
+    {
+      "epoch": 1.4052993130520117,
+      "grad_norm": 0.4052878853701832,
+      "learning_rate": 1.2809311997735697e-05,
+      "loss": 0.894,
+      "step": 179
+    },
+    {
+      "epoch": 1.4131501472031402,
+      "grad_norm": 0.4336142615902135,
+      "learning_rate": 1.2721034648453353e-05,
+      "loss": 0.8549,
+      "step": 180
+    },
+    {
+      "epoch": 1.4210009813542688,
+      "grad_norm": 0.4240407085293745,
+      "learning_rate": 1.2632527695645993e-05,
+      "loss": 0.8494,
+      "step": 181
+    },
+    {
+      "epoch": 1.4288518155053975,
+      "grad_norm": 0.39884877126677765,
+      "learning_rate": 1.2543798607615566e-05,
+      "loss": 0.87,
+      "step": 182
+    },
+    {
+      "epoch": 1.436702649656526,
+      "grad_norm": 0.4135733995550398,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.8461,
+      "step": 183
+    },
+    {
+      "epoch": 1.4445534838076546,
+      "grad_norm": 0.39163760815325666,
+      "learning_rate": 1.2365703992181425e-05,
+      "loss": 0.8542,
+      "step": 184
+    },
+    {
+      "epoch": 1.452404317958783,
+      "grad_norm": 0.3915987331953743,
+      "learning_rate": 1.2276353492572937e-05,
+      "loss": 0.8968,
+      "step": 185
+    },
+    {
+      "epoch": 1.4602551521099116,
+      "grad_norm": 0.43250371992921505,
+      "learning_rate": 1.218681091206376e-05,
+      "loss": 0.8688,
+      "step": 186
+    },
+    {
+      "epoch": 1.4681059862610402,
+      "grad_norm": 0.4116103269475378,
+      "learning_rate": 1.2097083806343104e-05,
+      "loss": 0.8571,
+      "step": 187
+    },
+    {
+      "epoch": 1.475956820412169,
+      "grad_norm": 0.4202792921734467,
+      "learning_rate": 1.2007179746670592e-05,
+      "loss": 0.8803,
+      "step": 188
+    },
+    {
+      "epoch": 1.4838076545632974,
+      "grad_norm": 0.40992910867999444,
+      "learning_rate": 1.1917106319237386e-05,
+      "loss": 0.8607,
+      "step": 189
+    },
+    {
+      "epoch": 1.491658488714426,
+      "grad_norm": 0.39815422761839314,
+      "learning_rate": 1.1826871124526072e-05,
+      "loss": 0.8989,
+      "step": 190
+    },
+    {
+      "epoch": 1.4995093228655545,
+      "grad_norm": 0.4408558658879014,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.8697,
+      "step": 191
+    },
+    {
+      "epoch": 1.507360157016683,
+      "grad_norm": 0.4002929921626025,
+      "learning_rate": 1.164594590280734e-05,
+      "loss": 0.8665,
+      "step": 192
+    },
+    {
+      "epoch": 1.5152109911678115,
+      "grad_norm": 0.38184469062528603,
+      "learning_rate": 1.1555271142444433e-05,
+      "loss": 0.861,
+      "step": 193
+    },
+    {
+      "epoch": 1.52306182531894,
+      "grad_norm": 0.399248837333263,
+      "learning_rate": 1.1464465146804218e-05,
+      "loss": 0.8429,
+      "step": 194
+    },
+    {
+      "epoch": 1.5309126594700686,
+      "grad_norm": 0.4399674734862063,
+      "learning_rate": 1.1373535578184083e-05,
+      "loss": 0.8429,
+      "step": 195
+    },
+    {
+      "epoch": 1.5387634936211971,
+      "grad_norm": 0.433354945977663,
+      "learning_rate": 1.1282490109308633e-05,
+      "loss": 0.8496,
+      "step": 196
+    },
+    {
+      "epoch": 1.5466143277723257,
+      "grad_norm": 0.42730902016328437,
+      "learning_rate": 1.1191336422682237e-05,
+      "loss": 0.8732,
+      "step": 197
+    },
+    {
+      "epoch": 1.5544651619234544,
+      "grad_norm": 0.39107521766059133,
+      "learning_rate": 1.1100082209940795e-05,
+      "loss": 0.8629,
+      "step": 198
+    },
+    {
+      "epoch": 1.562315996074583,
+      "grad_norm": 0.47259826332285304,
+      "learning_rate": 1.1008735171202685e-05,
+      "loss": 0.8533,
+      "step": 199
+    },
+    {
+      "epoch": 1.5701668302257115,
+      "grad_norm": 0.3998052386826209,
+      "learning_rate": 1.0917303014419036e-05,
+      "loss": 0.8742,
+      "step": 200
+    },
+    {
+      "epoch": 1.57801766437684,
+      "grad_norm": 0.4268905566447301,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.9009,
+      "step": 201
+    },
+    {
+      "epoch": 1.5858684985279687,
+      "grad_norm": 0.45903190858962667,
+      "learning_rate": 1.0734214213780355e-05,
+      "loss": 0.8756,
+      "step": 202
+    },
+    {
+      "epoch": 1.5937193326790973,
+      "grad_norm": 0.4510587783898759,
+      "learning_rate": 1.0642573019134703e-05,
+      "loss": 0.9155,
+      "step": 203
+    },
+    {
+      "epoch": 1.6015701668302258,
+      "grad_norm": 0.4120154923450346,
+      "learning_rate": 1.0550877603558656e-05,
+      "loss": 0.8733,
+      "step": 204
+    },
+    {
+      "epoch": 1.6094210009813543,
+      "grad_norm": 0.42095221498782726,
+      "learning_rate": 1.045913570439972e-05,
+      "loss": 0.8403,
+      "step": 205
+    },
+    {
+      "epoch": 1.6172718351324828,
+      "grad_norm": 0.37496725026140443,
+      "learning_rate": 1.0367355062927726e-05,
+      "loss": 0.8526,
+      "step": 206
+    },
+    {
+      "epoch": 1.6251226692836114,
+      "grad_norm": 0.4879740805171111,
+      "learning_rate": 1.0275543423681622e-05,
+      "loss": 0.8828,
+      "step": 207
+    },
+    {
+      "epoch": 1.63297350343474,
+      "grad_norm": 0.3831688177948347,
+      "learning_rate": 1.0183708533815975e-05,
+      "loss": 0.8428,
+      "step": 208
+    },
+    {
+      "epoch": 1.6408243375858684,
+      "grad_norm": 0.39284860770295016,
+      "learning_rate": 1.0091858142447266e-05,
+      "loss": 0.8779,
+      "step": 209
+    },
+    {
+      "epoch": 1.648675171736997,
+      "grad_norm": 0.40299661643677487,
+      "learning_rate": 1e-05,
+      "loss": 0.8658,
+      "step": 210
+    },
+    {
+      "epoch": 1.6565260058881255,
+      "grad_norm": 0.3836614493240331,
+      "learning_rate": 9.908141857552737e-06,
+      "loss": 0.8668,
+      "step": 211
+    },
+    {
+      "epoch": 1.664376840039254,
+      "grad_norm": 0.42491901903278484,
+      "learning_rate": 9.816291466184025e-06,
+      "loss": 0.8511,
+      "step": 212
+    },
+    {
+      "epoch": 1.6722276741903828,
+      "grad_norm": 0.3861624286850164,
+      "learning_rate": 9.724456576318383e-06,
+      "loss": 0.8798,
+      "step": 213
+    },
+    {
+      "epoch": 1.6800785083415113,
+      "grad_norm": 0.38505340457370013,
+      "learning_rate": 9.632644937072277e-06,
+      "loss": 0.8801,
+      "step": 214
+    },
+    {
+      "epoch": 1.6879293424926398,
+      "grad_norm": 0.41567977482219437,
+      "learning_rate": 9.540864295600282e-06,
+      "loss": 0.8876,
+      "step": 215
+    },
+    {
+      "epoch": 1.6957801766437686,
+      "grad_norm": 0.37371511146319797,
+      "learning_rate": 9.449122396441344e-06,
+      "loss": 0.8382,
+      "step": 216
+    },
+    {
+      "epoch": 1.703631010794897,
+      "grad_norm": 0.39807379798708376,
+      "learning_rate": 9.3574269808653e-06,
+      "loss": 0.8539,
+      "step": 217
+    },
+    {
+      "epoch": 1.7114818449460256,
+      "grad_norm": 0.386156219613775,
+      "learning_rate": 9.265785786219647e-06,
+      "loss": 0.8627,
+      "step": 218
+    },
+    {
+      "epoch": 1.7193326790971541,
+      "grad_norm": 0.38551764430241436,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.8526,
+      "step": 219
+    },
+    {
+      "epoch": 1.7271835132482827,
+      "grad_norm": 0.3833244794290772,
+      "learning_rate": 9.082696985580964e-06,
+      "loss": 0.8336,
+      "step": 220
+    },
+    {
+      "epoch": 1.7350343473994112,
+      "grad_norm": 0.46306324449457525,
+      "learning_rate": 8.991264828797319e-06,
+      "loss": 0.8528,
+      "step": 221
+    },
+    {
+      "epoch": 1.7428851815505397,
+      "grad_norm": 0.39868980942764537,
+      "learning_rate": 8.899917790059208e-06,
+      "loss": 0.8701,
+      "step": 222
+    },
+    {
+      "epoch": 1.7507360157016683,
+      "grad_norm": 0.38286594962238124,
+      "learning_rate": 8.808663577317765e-06,
+      "loss": 0.8649,
+      "step": 223
+    },
+    {
+      "epoch": 1.7585868498527968,
+      "grad_norm": 0.37622320497528744,
+      "learning_rate": 8.717509890691369e-06,
+      "loss": 0.8574,
+      "step": 224
+    },
+    {
+      "epoch": 1.7664376840039253,
+      "grad_norm": 0.3948944514950146,
+      "learning_rate": 8.626464421815919e-06,
+      "loss": 0.875,
+      "step": 225
+    },
+    {
+      "epoch": 1.7742885181550538,
+      "grad_norm": 0.3872312356708582,
+      "learning_rate": 8.535534853195786e-06,
+      "loss": 0.8687,
+      "step": 226
+    },
+    {
+      "epoch": 1.7821393523061824,
+      "grad_norm": 0.3925074851276092,
+      "learning_rate": 8.444728857555572e-06,
+      "loss": 0.8387,
+      "step": 227
+    },
+    {
+      "epoch": 1.7899901864573111,
+      "grad_norm": 0.38063520470964507,
+      "learning_rate": 8.35405409719266e-06,
+      "loss": 0.8777,
+      "step": 228
+    },
+    {
+      "epoch": 1.7978410206084396,
+      "grad_norm": 0.4125840435721029,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.8563,
+      "step": 229
+    },
+    {
+      "epoch": 1.8056918547595682,
+      "grad_norm": 0.40829808418504204,
+      "learning_rate": 8.173128875473933e-06,
+      "loss": 0.8736,
+      "step": 230
+    },
+    {
+      "epoch": 1.813542688910697,
+      "grad_norm": 0.412901044911201,
+      "learning_rate": 8.082893680762619e-06,
+      "loss": 0.8701,
+      "step": 231
+    },
+    {
+      "epoch": 1.8213935230618254,
+      "grad_norm": 0.38461905360798304,
+      "learning_rate": 7.99282025332941e-06,
+      "loss": 0.8372,
+      "step": 232
+    },
+    {
+      "epoch": 1.829244357212954,
+      "grad_norm": 0.37548970962969785,
+      "learning_rate": 7.902916193656898e-06,
+      "loss": 0.8411,
+      "step": 233
+    },
+    {
+      "epoch": 1.8370951913640825,
+      "grad_norm": 0.3827315486504844,
+      "learning_rate": 7.813189087936243e-06,
+      "loss": 0.8759,
+      "step": 234
+    },
+    {
+      "epoch": 1.844946025515211,
+      "grad_norm": 0.3874979575477364,
+      "learning_rate": 7.72364650742707e-06,
+      "loss": 0.8486,
+      "step": 235
+    },
+    {
+      "epoch": 1.8527968596663396,
+      "grad_norm": 0.3790848390909267,
+      "learning_rate": 7.634296007818576e-06,
+      "loss": 0.8716,
+      "step": 236
+    },
+    {
+      "epoch": 1.860647693817468,
+      "grad_norm": 0.378286581207217,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.8586,
+      "step": 237
+    },
+    {
+      "epoch": 1.8684985279685966,
+      "grad_norm": 0.39189419384474045,
+      "learning_rate": 7.456201392384437e-06,
+      "loss": 0.8283,
+      "step": 238
+    },
+    {
+      "epoch": 1.8763493621197251,
+      "grad_norm": 0.3847866457012834,
+      "learning_rate": 7.367472304354011e-06,
+      "loss": 0.8389,
+      "step": 239
+    },
+    {
+      "epoch": 1.8842001962708537,
+      "grad_norm": 0.4067072024420457,
+      "learning_rate": 7.278965351546648e-06,
+      "loss": 0.8624,
+      "step": 240
+    },
+    {
+      "epoch": 1.8920510304219822,
+      "grad_norm": 0.4160909228062074,
+      "learning_rate": 7.190688002264308e-06,
+      "loss": 0.8793,
+      "step": 241
+    },
+    {
+      "epoch": 1.899901864573111,
+      "grad_norm": 0.3796773233754196,
+      "learning_rate": 7.102647705434755e-06,
+      "loss": 0.849,
+      "step": 242
+    },
+    {
+      "epoch": 1.9077526987242395,
+      "grad_norm": 0.37688029078745,
+      "learning_rate": 7.014851889983058e-06,
+      "loss": 0.8512,
+      "step": 243
+    },
+    {
+      "epoch": 1.915603532875368,
+      "grad_norm": 0.3772729772351474,
+      "learning_rate": 6.927307964204695e-06,
+      "loss": 0.8467,
+      "step": 244
+    },
+    {
+      "epoch": 1.9234543670264965,
+      "grad_norm": 0.3857865403863187,
+      "learning_rate": 6.840023315140476e-06,
+      "loss": 0.8569,
+      "step": 245
+    },
+    {
+      "epoch": 1.9313052011776253,
+      "grad_norm": 0.3888642949537793,
+      "learning_rate": 6.7530053079531664e-06,
+      "loss": 0.9132,
+      "step": 246
+    },
+    {
+      "epoch": 1.9391560353287538,
+      "grad_norm": 0.3710335787976803,
+      "learning_rate": 6.666261285306048e-06,
+      "loss": 0.8372,
+      "step": 247
+    },
+    {
+      "epoch": 1.9470068694798823,
+      "grad_norm": 0.3943558384485135,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.8724,
+      "step": 248
+    },
+    {
+      "epoch": 1.9548577036310109,
+      "grad_norm": 0.3906737173367764,
+      "learning_rate": 6.4936244480724575e-06,
+      "loss": 0.8388,
+      "step": 249
+    },
+    {
+      "epoch": 1.9627085377821394,
+      "grad_norm": 0.3991267811889445,
+      "learning_rate": 6.407746200748628e-06,
+      "loss": 0.8312,
+      "step": 250
+    },
+    {
+      "epoch": 1.970559371933268,
+      "grad_norm": 0.4008187894805008,
+      "learning_rate": 6.322171071261071e-06,
+      "loss": 0.8826,
+      "step": 251
+    },
+    {
+      "epoch": 1.9784102060843964,
+      "grad_norm": 0.38411143405458265,
+      "learning_rate": 6.236906280521646e-06,
+      "loss": 0.8489,
+      "step": 252
+    },
+    {
+      "epoch": 1.986261040235525,
+      "grad_norm": 0.3640182845276182,
+      "learning_rate": 6.151959023255545e-06,
+      "loss": 0.855,
+      "step": 253
+    },
+    {
+      "epoch": 1.9941118743866535,
+      "grad_norm": 0.3960509553796272,
+      "learning_rate": 6.067336467394169e-06,
+      "loss": 0.8393,
+      "step": 254
+    },
+    {
+      "epoch": 1.9941118743866535,
+      "eval_loss": 0.997579038143158,
+      "eval_runtime": 88.1649,
+      "eval_samples_per_second": 3.051,
+      "eval_steps_per_second": 0.193,
+      "step": 254
+    },
+    {
+      "epoch": 2.001962708537782,
+      "grad_norm": 0.43072891263502616,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.831,
+      "step": 255
+    },
+    {
+      "epoch": 2.0098135426889105,
+      "grad_norm": 0.7188075313075105,
+      "learning_rate": 5.8990939940156e-06,
+      "loss": 0.7745,
+      "step": 256
+    },
+    {
+      "epoch": 2.017664376840039,
+      "grad_norm": 0.5896401870728147,
+      "learning_rate": 5.815488272960388e-06,
+      "loss": 0.7559,
+      "step": 257
+    },
+    {
+      "epoch": 2.0255152109911676,
+      "grad_norm": 0.577607354577268,
+      "learning_rate": 5.732235645035964e-06,
+      "loss": 0.7476,
+      "step": 258
+    },
+    {
+      "epoch": 2.0333660451422966,
+      "grad_norm": 0.622792465906415,
+      "learning_rate": 5.649343135179271e-06,
+      "loss": 0.7739,
+      "step": 259
+    },
+    {
+      "epoch": 2.041216879293425,
+      "grad_norm": 0.5137456244608113,
+      "learning_rate": 5.566817737940142e-06,
+      "loss": 0.7293,
+      "step": 260
+    },
+    {
+      "epoch": 2.0490677134445536,
+      "grad_norm": 0.5566993280492001,
+      "learning_rate": 5.484666416891109e-06,
+      "loss": 0.7114,
+      "step": 261
+    },
+    {
+      "epoch": 2.056918547595682,
+      "grad_norm": 0.5919083337200165,
+      "learning_rate": 5.4028961040397765e-06,
+      "loss": 0.7229,
+      "step": 262
+    },
+    {
+      "epoch": 2.0647693817468107,
+      "grad_norm": 0.5378683392601922,
+      "learning_rate": 5.321513699243924e-06,
+      "loss": 0.7212,
+      "step": 263
+    },
+    {
+      "epoch": 2.072620215897939,
+      "grad_norm": 0.45647692363289727,
+      "learning_rate": 5.240526069629265e-06,
+      "loss": 0.7229,
+      "step": 264
+    },
+    {
+      "epoch": 2.0804710500490677,
+      "grad_norm": 0.4887674415583664,
+      "learning_rate": 5.159940049010015e-06,
+      "loss": 0.767,
+      "step": 265
+    },
+    {
+      "epoch": 2.0883218842001963,
+      "grad_norm": 0.5510586431679284,
+      "learning_rate": 5.079762437312219e-06,
+      "loss": 0.743,
+      "step": 266
+    },
+    {
+      "epoch": 2.096172718351325,
+      "grad_norm": 0.4578645465622997,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.7463,
+      "step": 267
+    },
+    {
+      "epoch": 2.1040235525024533,
+      "grad_norm": 0.46155494471555,
+      "learning_rate": 4.9206594675046595e-06,
+      "loss": 0.7164,
+      "step": 268
+    },
+    {
+      "epoch": 2.111874386653582,
+      "grad_norm": 0.48291155406692277,
+      "learning_rate": 4.8417475346567635e-06,
+      "loss": 0.7431,
+      "step": 269
+    },
+    {
+      "epoch": 2.1197252208047104,
+      "grad_norm": 0.4713045038199255,
+      "learning_rate": 4.763270860121222e-06,
+      "loss": 0.7553,
+      "step": 270
+    },
+    {
+      "epoch": 2.127576054955839,
+      "grad_norm": 0.4204415558473321,
+      "learning_rate": 4.685236065835443e-06,
+      "loss": 0.7017,
+      "step": 271
+    },
+    {
+      "epoch": 2.1354268891069674,
+      "grad_norm": 0.5026853482732088,
+      "learning_rate": 4.607649736450539e-06,
+      "loss": 0.7555,
+      "step": 272
+    },
+    {
+      "epoch": 2.1432777232580964,
+      "grad_norm": 0.49743916152047296,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.7713,
+      "step": 273
+    },
+    {
+      "epoch": 2.151128557409225,
+      "grad_norm": 0.42488292265674255,
+      "learning_rate": 4.453848621225913e-06,
+      "loss": 0.7336,
+      "step": 274
+    },
+    {
+      "epoch": 2.1589793915603535,
+      "grad_norm": 0.42874175983669743,
+      "learning_rate": 4.3776468132724605e-06,
+      "loss": 0.7178,
+      "step": 275
+    },
+    {
+      "epoch": 2.166830225711482,
+      "grad_norm": 0.42883007812800905,
+      "learning_rate": 4.301919424897339e-06,
+      "loss": 0.7665,
+      "step": 276
+    },
+    {
+      "epoch": 2.1746810598626105,
+      "grad_norm": 0.45184945057766773,
+      "learning_rate": 4.226672846050538e-06,
+      "loss": 0.7285,
+      "step": 277
+    },
+    {
+      "epoch": 2.182531894013739,
+      "grad_norm": 0.4611091282623315,
+      "learning_rate": 4.151913426110864e-06,
+      "loss": 0.7321,
+      "step": 278
+    },
+    {
+      "epoch": 2.1903827281648676,
+      "grad_norm": 0.41794265030453176,
+      "learning_rate": 4.077647473350201e-06,
+      "loss": 0.7175,
+      "step": 279
+    },
+    {
+      "epoch": 2.198233562315996,
+      "grad_norm": 0.4243419492016501,
+      "learning_rate": 4.003881254401183e-06,
+      "loss": 0.7404,
+      "step": 280
+    },
+    {
+      "epoch": 2.2060843964671246,
+      "grad_norm": 0.4442497933245384,
+      "learning_rate": 3.930620993728434e-06,
+      "loss": 0.7447,
+      "step": 281
+    },
+    {
+      "epoch": 2.213935230618253,
+      "grad_norm": 0.42081984589044574,
+      "learning_rate": 3.857872873103322e-06,
+      "loss": 0.7095,
+      "step": 282
+    },
+    {
+      "epoch": 2.2217860647693817,
+      "grad_norm": 0.40331371462546917,
+      "learning_rate": 3.7856430310823546e-06,
+      "loss": 0.7313,
+      "step": 283
+    },
+    {
+      "epoch": 2.22963689892051,
+      "grad_norm": 0.40483189883145515,
+      "learning_rate": 3.7139375624891795e-06,
+      "loss": 0.718,
+      "step": 284
+    },
+    {
+      "epoch": 2.2374877330716387,
+      "grad_norm": 0.42614915501351497,
+      "learning_rate": 3.6427625179003223e-06,
+      "loss": 0.7415,
+      "step": 285
+    },
+    {
+      "epoch": 2.2453385672227673,
+      "grad_norm": 0.4330393696080875,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.7436,
+      "step": 286
+    },
+    {
+      "epoch": 2.253189401373896,
+      "grad_norm": 0.40400852616372396,
+      "learning_rate": 3.5020276787464058e-06,
+      "loss": 0.7329,
+      "step": 287
+    },
+    {
+      "epoch": 2.2610402355250248,
+      "grad_norm": 0.42978730056470976,
+      "learning_rate": 3.4324797595226567e-06,
+      "loss": 0.7669,
+      "step": 288
+    },
+    {
+      "epoch": 2.2688910696761533,
+      "grad_norm": 0.4131331700795359,
+      "learning_rate": 3.3634860139837877e-06,
+      "loss": 0.7283,
+      "step": 289
+    },
+    {
+      "epoch": 2.276741903827282,
+      "grad_norm": 0.406011895392433,
+      "learning_rate": 3.2950522638885106e-06,
+      "loss": 0.772,
+      "step": 290
+    },
+    {
+      "epoch": 2.2845927379784103,
+      "grad_norm": 0.5920475511930268,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.7298,
+      "step": 291
+    },
+    {
+      "epoch": 2.292443572129539,
+      "grad_norm": 0.42303105090010457,
+      "learning_rate": 3.1598878003115694e-06,
+      "loss": 0.7339,
+      "step": 292
+    },
+    {
+      "epoch": 2.3002944062806674,
+      "grad_norm": 0.40741794860570885,
+      "learning_rate": 3.0931684921375572e-06,
+      "loss": 0.7162,
+      "step": 293
+    },
+    {
+      "epoch": 2.308145240431796,
+      "grad_norm": 0.4092973493096159,
+      "learning_rate": 3.0270319890600465e-06,
+      "loss": 0.7299,
+      "step": 294
+    },
+    {
+      "epoch": 2.3159960745829244,
+      "grad_norm": 0.4139310992654331,
+      "learning_rate": 2.9614838717408866e-06,
+      "loss": 0.7263,
+      "step": 295
+    },
+    {
+      "epoch": 2.323846908734053,
+      "grad_norm": 0.4129053342570891,
+      "learning_rate": 2.89652967119336e-06,
+      "loss": 0.7432,
+      "step": 296
+    },
+    {
+      "epoch": 2.3316977428851815,
+      "grad_norm": 0.4191575482697591,
+      "learning_rate": 2.8321748683154893e-06,
+      "loss": 0.7799,
+      "step": 297
+    },
+    {
+      "epoch": 2.33954857703631,
+      "grad_norm": 0.39663461320365995,
+      "learning_rate": 2.7684248934275327e-06,
+      "loss": 0.6982,
+      "step": 298
+    },
+    {
+      "epoch": 2.3473994111874386,
+      "grad_norm": 0.402817187584292,
+      "learning_rate": 2.7052851258137936e-06,
+      "loss": 0.7152,
+      "step": 299
+    },
+    {
+      "epoch": 2.355250245338567,
+      "grad_norm": 0.40411646566528947,
+      "learning_rate": 2.642760893268684e-06,
+      "loss": 0.7245,
+      "step": 300
+    },
+    {
+      "epoch": 2.3631010794896956,
+      "grad_norm": 0.4015793634544117,
+      "learning_rate": 2.580857471647186e-06,
+      "loss": 0.7099,
+      "step": 301
+    },
+    {
+      "epoch": 2.370951913640824,
+      "grad_norm": 0.40272965776545055,
+      "learning_rate": 2.519580084419646e-06,
+      "loss": 0.7722,
+      "step": 302
+    },
+    {
+      "epoch": 2.378802747791953,
+      "grad_norm": 0.39782942580042024,
+      "learning_rate": 2.4589339022310386e-06,
+      "loss": 0.7645,
+      "step": 303
+    },
+    {
+      "epoch": 2.3866535819430816,
+      "grad_norm": 0.40881226326614195,
+      "learning_rate": 2.3989240424646355e-06,
+      "loss": 0.7722,
+      "step": 304
+    },
+    {
+      "epoch": 2.39450441609421,
+      "grad_norm": 0.43205576259137957,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.7419,
+      "step": 305
+    },
+    {
+      "epoch": 2.4023552502453387,
+      "grad_norm": 0.39906675706682876,
+      "learning_rate": 2.2808334908367914e-06,
+      "loss": 0.712,
+      "step": 306
+    },
+    {
+      "epoch": 2.410206084396467,
+      "grad_norm": 0.398424598259541,
+      "learning_rate": 2.2227627635698624e-06,
+      "loss": 0.7537,
+      "step": 307
+    },
+    {
+      "epoch": 2.4180569185475957,
+      "grad_norm": 0.4149034287273452,
+      "learning_rate": 2.165348287073339e-06,
+      "loss": 0.738,
+      "step": 308
+    },
+    {
+      "epoch": 2.4259077526987243,
+      "grad_norm": 0.3938810528645433,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.7208,
+      "step": 309
+    },
+    {
+      "epoch": 2.433758586849853,
+      "grad_norm": 0.40657363748699743,
+      "learning_rate": 2.052507409363004e-06,
+      "loss": 0.7112,
+      "step": 310
+    },
+    {
+      "epoch": 2.4416094210009813,
+      "grad_norm": 0.4053156932256877,
+      "learning_rate": 1.9970905297711606e-06,
+      "loss": 0.7513,
+      "step": 311
+    },
+    {
+      "epoch": 2.44946025515211,
+      "grad_norm": 0.402958620543919,
+      "learning_rate": 1.9423489433902186e-06,
+      "loss": 0.7155,
+      "step": 312
+    },
+    {
+      "epoch": 2.4573110893032384,
+      "grad_norm": 0.40034129785514294,
+      "learning_rate": 1.8882872693679787e-06,
+      "loss": 0.7437,
+      "step": 313
+    },
+    {
+      "epoch": 2.465161923454367,
+      "grad_norm": 0.39745192695598786,
+      "learning_rate": 1.8349100694805711e-06,
+      "loss": 0.7473,
+      "step": 314
+    },
+    {
+      "epoch": 2.4730127576054954,
+      "grad_norm": 0.40380072949324297,
+      "learning_rate": 1.7822218477475496e-06,
+      "loss": 0.7324,
+      "step": 315
+    },
+    {
+      "epoch": 2.480863591756624,
+      "grad_norm": 0.39226384000228454,
+      "learning_rate": 1.7302270500518181e-06,
+      "loss": 0.7449,
+      "step": 316
+    },
+    {
+      "epoch": 2.4887144259077525,
+      "grad_norm": 0.39658915645074944,
+      "learning_rate": 1.6789300637645e-06,
+      "loss": 0.723,
+      "step": 317
+    },
+    {
+      "epoch": 2.4965652600588815,
+      "grad_norm": 0.44887663192812466,
+      "learning_rate": 1.6283352173747148e-06,
+      "loss": 0.7425,
+      "step": 318
+    },
+    {
+      "epoch": 2.5044160942100095,
+      "grad_norm": 0.4025906294392866,
+      "learning_rate": 1.578446780124344e-06,
+      "loss": 0.7464,
+      "step": 319
+    },
+    {
+      "epoch": 2.5122669283611385,
+      "grad_norm": 0.39593288856275255,
+      "learning_rate": 1.5292689616477808e-06,
+      "loss": 0.7306,
+      "step": 320
+    },
+    {
+      "epoch": 2.520117762512267,
+      "grad_norm": 0.8163857581797331,
+      "learning_rate": 1.4808059116167306e-06,
+      "loss": 0.7299,
+      "step": 321
+    },
+    {
+      "epoch": 2.5279685966633956,
+      "grad_norm": 0.4214612635268738,
+      "learning_rate": 1.4330617193900365e-06,
+      "loss": 0.7261,
+      "step": 322
+    },
+    {
+      "epoch": 2.535819430814524,
+      "grad_norm": 0.3961431274309664,
+      "learning_rate": 1.3860404136686411e-06,
+      "loss": 0.7473,
+      "step": 323
+    },
+    {
+      "epoch": 2.5436702649656526,
+      "grad_norm": 0.39004891440687217,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.7517,
+      "step": 324
+    },
+    {
+      "epoch": 2.551521099116781,
+      "grad_norm": 0.41561524877062966,
+      "learning_rate": 1.294182271221377e-06,
+      "loss": 0.7162,
+      "step": 325
+    },
+    {
+      "epoch": 2.5593719332679097,
+      "grad_norm": 0.3888375314842916,
+      "learning_rate": 1.2493531855740626e-06,
+      "loss": 0.738,
+      "step": 326
+    },
+    {
+      "epoch": 2.567222767419038,
+      "grad_norm": 0.4153069092738427,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.7328,
+      "step": 327
+    },
+    {
+      "epoch": 2.5750736015701667,
+      "grad_norm": 0.39835093714606346,
+      "learning_rate": 1.1619138987200562e-06,
+      "loss": 0.7472,
+      "step": 328
+    },
+    {
+      "epoch": 2.5829244357212953,
+      "grad_norm": 0.40261441538060305,
+      "learning_rate": 1.1193110757246251e-06,
+      "loss": 0.7261,
+      "step": 329
+    },
+    {
+      "epoch": 2.590775269872424,
+      "grad_norm": 0.39533691263220494,
+      "learning_rate": 1.0774576138160596e-06,
+      "loss": 0.7024,
+      "step": 330
+    },
+    {
+      "epoch": 2.5986261040235528,
+      "grad_norm": 0.41713533012692194,
+      "learning_rate": 1.0363570446297999e-06,
+      "loss": 0.7322,
+      "step": 331
+    },
+    {
+      "epoch": 2.606476938174681,
+      "grad_norm": 0.40104402435709136,
+      "learning_rate": 9.960128362714637e-07,
+      "loss": 0.7433,
+      "step": 332
+    },
+    {
+      "epoch": 2.61432777232581,
+      "grad_norm": 0.44002481329404,
+      "learning_rate": 9.564283930242258e-07,
+      "loss": 0.723,
+      "step": 333
+    },
+    {
+      "epoch": 2.622178606476938,
+      "grad_norm": 0.40444000612414294,
+      "learning_rate": 9.176070550615379e-07,
+      "loss": 0.7244,
+      "step": 334
+    },
+    {
+      "epoch": 2.630029440628067,
+      "grad_norm": 0.4325549460655756,
+      "learning_rate": 8.79552098165296e-07,
+      "loss": 0.7271,
+      "step": 335
+    },
+    {
+      "epoch": 2.6378802747791954,
+      "grad_norm": 0.39538678921804654,
+      "learning_rate": 8.42266733449425e-07,
+      "loss": 0.7537,
+      "step": 336
+    },
+    {
+      "epoch": 2.645731108930324,
+      "grad_norm": 0.39921777289111915,
+      "learning_rate": 8.057541070889229e-07,
+      "loss": 0.7449,
+      "step": 337
+    },
+    {
+      "epoch": 2.6535819430814525,
+      "grad_norm": 0.39092167777234016,
+      "learning_rate": 7.700173000543742e-07,
+      "loss": 0.7201,
+      "step": 338
+    },
+    {
+      "epoch": 2.661432777232581,
+      "grad_norm": 0.40392908365813746,
+      "learning_rate": 7.350593278519824e-07,
+      "loss": 0.7044,
+      "step": 339
+    },
+    {
+      "epoch": 2.6692836113837095,
+      "grad_norm": 0.399420619831215,
+      "learning_rate": 7.00883140269123e-07,
+      "loss": 0.749,
+      "step": 340
+    },
+    {
+      "epoch": 2.677134445534838,
+      "grad_norm": 0.40466792504791993,
+      "learning_rate": 6.67491621125429e-07,
+      "loss": 0.7316,
+      "step": 341
+    },
+    {
+      "epoch": 2.6849852796859666,
+      "grad_norm": 0.3885585239605456,
+      "learning_rate": 6.348875880294536e-07,
+      "loss": 0.7226,
+      "step": 342
+    },
+    {
+      "epoch": 2.692836113837095,
+      "grad_norm": 0.4040266162935783,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.7493,
+      "step": 343
+    },
+    {
+      "epoch": 2.7006869479882236,
+      "grad_norm": 0.5671755345323075,
+      "learning_rate": 5.720529179385659e-07,
+      "loss": 0.7383,
+      "step": 344
+    },
+    {
+      "epoch": 2.708537782139352,
+      "grad_norm": 0.40153142940662157,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.7282,
+      "step": 345
+    },
+    {
+      "epoch": 2.716388616290481,
+      "grad_norm": 0.3988759611946295,
+      "learning_rate": 5.124003377490582e-07,
+      "loss": 0.7126,
+      "step": 346
+    },
+    {
+      "epoch": 2.724239450441609,
+      "grad_norm": 0.3995576946976954,
+      "learning_rate": 4.837736653040825e-07,
+      "loss": 0.7356,
+      "step": 347
+    },
+    {
+      "epoch": 2.732090284592738,
+      "grad_norm": 0.40525064088869744,
+      "learning_rate": 4.5594998120492505e-07,
+      "loss": 0.7392,
+      "step": 348
+    },
+    {
+      "epoch": 2.7399411187438667,
+      "grad_norm": 0.39485440118634596,
+      "learning_rate": 4.2893163324085886e-07,
+      "loss": 0.7555,
+      "step": 349
+    },
+    {
+      "epoch": 2.7477919528949952,
+      "grad_norm": 0.3953505684630469,
+      "learning_rate": 4.0272090124611086e-07,
+      "loss": 0.759,
+      "step": 350
+    },
+    {
+      "epoch": 2.7556427870461238,
+      "grad_norm": 0.4015694593262535,
+      "learning_rate": 3.773199969074959e-07,
+      "loss": 0.7721,
+      "step": 351
+    },
+    {
+      "epoch": 2.7634936211972523,
+      "grad_norm": 0.39785972086590143,
+      "learning_rate": 3.5273106357779585e-07,
+      "loss": 0.7403,
+      "step": 352
+    },
+    {
+      "epoch": 2.771344455348381,
+      "grad_norm": 0.39338079170444706,
+      "learning_rate": 3.2895617609489337e-07,
+      "loss": 0.7193,
+      "step": 353
+    },
+    {
+      "epoch": 2.7791952894995093,
+      "grad_norm": 0.40106967534157795,
+      "learning_rate": 3.059973406066963e-07,
+      "loss": 0.7575,
+      "step": 354
+    },
+    {
+      "epoch": 2.787046123650638,
+      "grad_norm": 0.39207275535615,
+      "learning_rate": 2.838564944018618e-07,
+      "loss": 0.7407,
+      "step": 355
+    },
+    {
+      "epoch": 2.7948969578017664,
+      "grad_norm": 0.38843134149786,
+      "learning_rate": 2.62535505746323e-07,
+      "loss": 0.7267,
+      "step": 356
+    },
+    {
+      "epoch": 2.802747791952895,
+      "grad_norm": 0.39469114149959683,
+      "learning_rate": 2.420361737256438e-07,
+      "loss": 0.7253,
+      "step": 357
+    },
+    {
+      "epoch": 2.8105986261040234,
+      "grad_norm": 0.39369639440819254,
+      "learning_rate": 2.22360228093208e-07,
+      "loss": 0.7293,
+      "step": 358
+    },
+    {
+      "epoch": 2.818449460255152,
+      "grad_norm": 0.4075421289278202,
+      "learning_rate": 2.035093291242607e-07,
+      "loss": 0.7516,
+      "step": 359
+    },
+    {
+      "epoch": 2.8263002944062805,
+      "grad_norm": 0.40225972984694325,
+      "learning_rate": 1.854850674758213e-07,
+      "loss": 0.7216,
+      "step": 360
+    },
+    {
+      "epoch": 2.8341511285574095,
+      "grad_norm": 0.39338786847062124,
+      "learning_rate": 1.6828896405244988e-07,
+      "loss": 0.7695,
+      "step": 361
+    },
+    {
+      "epoch": 2.8420019627085376,
+      "grad_norm": 0.4038122781289067,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.7431,
+      "step": 362
+    },
+    {
+      "epoch": 2.8498527968596665,
+      "grad_norm": 0.41309978437615624,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.7425,
+      "step": 363
+    },
+    {
+      "epoch": 2.857703631010795,
+      "grad_norm": 0.42117140315730617,
+      "learning_rate": 1.2168376323780652e-07,
+      "loss": 0.7304,
+      "step": 364
+    },
+    {
+      "epoch": 2.8655544651619236,
+      "grad_norm": 0.40569794939063863,
+      "learning_rate": 1.0781410234342093e-07,
+      "loss": 0.7064,
+      "step": 365
+    },
+    {
+      "epoch": 2.873405299313052,
+      "grad_norm": 0.39219918551845784,
+      "learning_rate": 9.47791536249676e-08,
+      "loss": 0.6775,
+      "step": 366
+    },
+    {
+      "epoch": 2.8812561334641806,
+      "grad_norm": 0.3934376699297971,
+      "learning_rate": 8.258001698397744e-08,
+      "loss": 0.7595,
+      "step": 367
+    },
+    {
+      "epoch": 2.889106967615309,
+      "grad_norm": 0.40550357139926846,
+      "learning_rate": 7.121772179535135e-08,
+      "loss": 0.7323,
+      "step": 368
+    },
+    {
+      "epoch": 2.8969578017664377,
+      "grad_norm": 0.4049202581172895,
+      "learning_rate": 6.069322682050516e-08,
+      "loss": 0.7491,
+      "step": 369
+    },
+    {
+      "epoch": 2.904808635917566,
+      "grad_norm": 0.39347508388168884,
+      "learning_rate": 5.10074201264632e-08,
+      "loss": 0.7261,
+      "step": 370
+    },
+    {
+      "epoch": 2.9126594700686947,
+      "grad_norm": 0.40813653261225263,
+      "learning_rate": 4.216111901092501e-08,
+      "loss": 0.7371,
+      "step": 371
+    },
+    {
+      "epoch": 2.9205103042198233,
+      "grad_norm": 0.40559311107877066,
+      "learning_rate": 3.4155069933301535e-08,
+      "loss": 0.7203,
+      "step": 372
+    },
+    {
+      "epoch": 2.928361138370952,
+      "grad_norm": 0.39971113625907556,
+      "learning_rate": 2.6989948451726643e-08,
+      "loss": 0.763,
+      "step": 373
+    },
+    {
+      "epoch": 2.9362119725220803,
+      "grad_norm": 0.40489368927937147,
+      "learning_rate": 2.066635916605386e-08,
+      "loss": 0.7453,
+      "step": 374
+    },
+    {
+      "epoch": 2.944062806673209,
+      "grad_norm": 0.4021143650346067,
+      "learning_rate": 1.518483566683826e-08,
+      "loss": 0.7108,
+      "step": 375
+    },
+    {
+      "epoch": 2.951913640824338,
+      "grad_norm": 0.3942497951111194,
+      "learning_rate": 1.0545840490313597e-08,
+      "loss": 0.7599,
+      "step": 376
+    },
+    {
+      "epoch": 2.959764474975466,
+      "grad_norm": 0.3953361295347161,
+      "learning_rate": 6.749765079363535e-09,
+      "loss": 0.7518,
+      "step": 377
+    },
+    {
+      "epoch": 2.967615309126595,
+      "grad_norm": 0.4106090374277888,
+      "learning_rate": 3.7969297504858445e-09,
+      "loss": 0.7213,
+      "step": 378
+    },
+    {
+      "epoch": 2.9754661432777234,
+      "grad_norm": 0.39869754415901865,
+      "learning_rate": 1.6875836667729073e-09,
+      "loss": 0.729,
+      "step": 379
+    },
+    {
+      "epoch": 2.983316977428852,
+      "grad_norm": 0.3875658253178697,
+      "learning_rate": 4.2190481687631736e-10,
+      "loss": 0.7433,
+      "step": 380
+    },
+    {
+      "epoch": 2.9911678115799805,
+      "grad_norm": 0.3895472615671169,
+      "learning_rate": 0.0,
+      "loss": 0.7166,
+      "step": 381
+    },
+    {
+      "epoch": 2.9911678115799805,
+      "eval_loss": 1.0287634134292603,
+      "eval_runtime": 88.0903,
+      "eval_samples_per_second": 3.054,
+      "eval_steps_per_second": 0.193,
+      "step": 381
+    },
+    {
+      "epoch": 2.9911678115799805,
+      "step": 381,
+      "total_flos": 159494952714240.0,
+      "train_loss": 0.9007005614871428,
+      "train_runtime": 67911.5352,
+      "train_samples_per_second": 0.72,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 381,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 159494952714240.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}