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-llama2
+  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-llama2
+
+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: 1.0380
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0183        | 0.9980 | 126  | 1.0127          |
+| 0.869         | 1.9960 | 252  | 1.0026          |
+| 0.714         | 2.9941 | 378  | 1.0380          |
+
+
+### 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": 2.994059405940594,
+    "total_flos": 158238674780160.0,
+    "train_loss": 0.8970171990533354,
+    "train_runtime": 67109.8008,
+    "train_samples": 61134,
+    "train_samples_per_second": 0.722,
+    "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 sha256:2f3be8e55bb255cd2c7dddf5fa5f087353ac62d8c7383838c9e1cd8cab5422bc
+size 4840396416

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fd67afdb2d4dc4ab5b8d20c36b22e679c02d427fda130f5819ef0ba720ac344
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fe28bed60d4067067cf28d19bab65cf64202bbf5fa129ef044e0859cd5bb69
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54b034d23dbbc5ab35163313cebe7eee45f3d86e2102ab0a56844a26799dfb8
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45fad17ae0b63365efb9d1cb1e17ee6d216d789957c9da66032ab5321e05987
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52523820d249772e255bbf93dfb651a2d25b7baf907d1e863732be9e56699f3b
+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": 2.994059405940594,
+    "total_flos": 158238674780160.0,
+    "train_loss": 0.8970171990533354,
+    "train_runtime": 67109.8008,
+    "train_samples": 61134,
+    "train_samples_per_second": 0.722,
+    "train_steps_per_second": 0.006
+}

trainer_state.json

@@ -0,0 +1,2712 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.994059405940594,
+  "eval_steps": 500,
+  "global_step": 378,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007920792079207921,
+      "grad_norm": 5.2691683098946545,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 1.568,
+      "step": 1
+    },
+    {
+      "epoch": 0.015841584158415842,
+      "grad_norm": 5.00511067394956,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 1.5221,
+      "step": 2
+    },
+    {
+      "epoch": 0.023762376237623763,
+      "grad_norm": 4.54506426631759,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 1.5171,
+      "step": 3
+    },
+    {
+      "epoch": 0.031683168316831684,
+      "grad_norm": 4.36896006607012,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 1.5391,
+      "step": 4
+    },
+    {
+      "epoch": 0.039603960396039604,
+      "grad_norm": 3.353266992703984,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 1.4111,
+      "step": 5
+    },
+    {
+      "epoch": 0.047524752475247525,
+      "grad_norm": 2.920541207093266,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 1.3994,
+      "step": 6
+    },
+    {
+      "epoch": 0.055445544554455446,
+      "grad_norm": 1.916780394273478,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 1.3978,
+      "step": 7
+    },
+    {
+      "epoch": 0.06336633663366337,
+      "grad_norm": 1.7850272367832638,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.3282,
+      "step": 8
+    },
+    {
+      "epoch": 0.07128712871287128,
+      "grad_norm": 1.7482580453609655,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 1.2986,
+      "step": 9
+    },
+    {
+      "epoch": 0.07920792079207921,
+      "grad_norm": 1.449543281626886,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 1.2898,
+      "step": 10
+    },
+    {
+      "epoch": 0.08712871287128712,
+      "grad_norm": 1.8720398819253754,
+      "learning_rate": 5.789473684210527e-06,
+      "loss": 1.2781,
+      "step": 11
+    },
+    {
+      "epoch": 0.09504950495049505,
+      "grad_norm": 2.2015426049634503,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 1.2935,
+      "step": 12
+    },
+    {
+      "epoch": 0.10297029702970296,
+      "grad_norm": 2.615874858377271,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 1.2973,
+      "step": 13
+    },
+    {
+      "epoch": 0.11089108910891089,
+      "grad_norm": 3.8682995800654187,
+      "learning_rate": 7.368421052631579e-06,
+      "loss": 1.2402,
+      "step": 14
+    },
+    {
+      "epoch": 0.1188118811881188,
+      "grad_norm": 2.746699538417491,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 1.2562,
+      "step": 15
+    },
+    {
+      "epoch": 0.12673267326732673,
+      "grad_norm": 2.682031995657898,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.2414,
+      "step": 16
+    },
+    {
+      "epoch": 0.13465346534653466,
+      "grad_norm": 2.9242715554029663,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 1.173,
+      "step": 17
+    },
+    {
+      "epoch": 0.14257425742574256,
+      "grad_norm": 2.7715021870832386,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 1.218,
+      "step": 18
+    },
+    {
+      "epoch": 0.1504950495049505,
+      "grad_norm": 2.3528632221189607,
+      "learning_rate": 1e-05,
+      "loss": 1.1863,
+      "step": 19
+    },
+    {
+      "epoch": 0.15841584158415842,
+      "grad_norm": 2.034765686956333,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.1888,
+      "step": 20
+    },
+    {
+      "epoch": 0.16633663366336635,
+      "grad_norm": 3.1288870944867666,
+      "learning_rate": 1.105263157894737e-05,
+      "loss": 1.1971,
+      "step": 21
+    },
+    {
+      "epoch": 0.17425742574257425,
+      "grad_norm": 2.195732986258774,
+      "learning_rate": 1.1578947368421053e-05,
+      "loss": 1.1866,
+      "step": 22
+    },
+    {
+      "epoch": 0.18217821782178217,
+      "grad_norm": 4.112336771867653,
+      "learning_rate": 1.2105263157894737e-05,
+      "loss": 1.1563,
+      "step": 23
+    },
+    {
+      "epoch": 0.1900990099009901,
+      "grad_norm": 3.6328533281903526,
+      "learning_rate": 1.263157894736842e-05,
+      "loss": 1.175,
+      "step": 24
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 1.6325540508979153,
+      "learning_rate": 1.3157894736842108e-05,
+      "loss": 1.1646,
+      "step": 25
+    },
+    {
+      "epoch": 0.20594059405940593,
+      "grad_norm": 3.9494616695340077,
+      "learning_rate": 1.3684210526315791e-05,
+      "loss": 1.1323,
+      "step": 26
+    },
+    {
+      "epoch": 0.21386138613861386,
+      "grad_norm": 3.27189931951213,
+      "learning_rate": 1.4210526315789475e-05,
+      "loss": 1.1408,
+      "step": 27
+    },
+    {
+      "epoch": 0.22178217821782178,
+      "grad_norm": 2.6804790210906573,
+      "learning_rate": 1.4736842105263159e-05,
+      "loss": 1.1319,
+      "step": 28
+    },
+    {
+      "epoch": 0.2297029702970297,
+      "grad_norm": 1.1471627340033614,
+      "learning_rate": 1.5263157894736846e-05,
+      "loss": 1.1482,
+      "step": 29
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "grad_norm": 2.002020630505531,
+      "learning_rate": 1.578947368421053e-05,
+      "loss": 1.1494,
+      "step": 30
+    },
+    {
+      "epoch": 0.24554455445544554,
+      "grad_norm": 2.4723778287869616,
+      "learning_rate": 1.6315789473684213e-05,
+      "loss": 1.1441,
+      "step": 31
+    },
+    {
+      "epoch": 0.25346534653465347,
+      "grad_norm": 2.229781993318989,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 1.1235,
+      "step": 32
+    },
+    {
+      "epoch": 0.2613861386138614,
+      "grad_norm": 1.7701112722120012,
+      "learning_rate": 1.736842105263158e-05,
+      "loss": 1.1126,
+      "step": 33
+    },
+    {
+      "epoch": 0.2693069306930693,
+      "grad_norm": 1.064748424759578,
+      "learning_rate": 1.7894736842105264e-05,
+      "loss": 1.1595,
+      "step": 34
+    },
+    {
+      "epoch": 0.27722772277227725,
+      "grad_norm": 1.2312931929901163,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 1.1668,
+      "step": 35
+    },
+    {
+      "epoch": 0.2851485148514851,
+      "grad_norm": 1.7551020997420819,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 1.0913,
+      "step": 36
+    },
+    {
+      "epoch": 0.29306930693069305,
+      "grad_norm": 1.7687041331840054,
+      "learning_rate": 1.9473684210526318e-05,
+      "loss": 1.1152,
+      "step": 37
+    },
+    {
+      "epoch": 0.300990099009901,
+      "grad_norm": 0.5975775886980378,
+      "learning_rate": 2e-05,
+      "loss": 1.1279,
+      "step": 38
+    },
+    {
+      "epoch": 0.3089108910891089,
+      "grad_norm": 1.7305083714637768,
+      "learning_rate": 1.999957311703368e-05,
+      "loss": 1.0947,
+      "step": 39
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 1.844146398722995,
+      "learning_rate": 1.9998292504580528e-05,
+      "loss": 1.0906,
+      "step": 40
+    },
+    {
+      "epoch": 0.32475247524752476,
+      "grad_norm": 0.7796143095441499,
+      "learning_rate": 1.9996158271974875e-05,
+      "loss": 1.1236,
+      "step": 41
+    },
+    {
+      "epoch": 0.3326732673267327,
+      "grad_norm": 1.5056201561723581,
+      "learning_rate": 1.9993170601430233e-05,
+      "loss": 1.0662,
+      "step": 42
+    },
+    {
+      "epoch": 0.3405940594059406,
+      "grad_norm": 1.8181218416149059,
+      "learning_rate": 1.9989329748023728e-05,
+      "loss": 1.1041,
+      "step": 43
+    },
+    {
+      "epoch": 0.3485148514851485,
+      "grad_norm": 1.0925270287101072,
+      "learning_rate": 1.9984636039674342e-05,
+      "loss": 1.1226,
+      "step": 44
+    },
+    {
+      "epoch": 0.3564356435643564,
+      "grad_norm": 0.9921305736361253,
+      "learning_rate": 1.9979089877114905e-05,
+      "loss": 1.0756,
+      "step": 45
+    },
+    {
+      "epoch": 0.36435643564356435,
+      "grad_norm": 1.2754799989749876,
+      "learning_rate": 1.997269173385788e-05,
+      "loss": 1.1173,
+      "step": 46
+    },
+    {
+      "epoch": 0.3722772277227723,
+      "grad_norm": 0.8010641417555526,
+      "learning_rate": 1.9965442156154947e-05,
+      "loss": 1.1113,
+      "step": 47
+    },
+    {
+      "epoch": 0.3801980198019802,
+      "grad_norm": 0.7444563010730426,
+      "learning_rate": 1.9957341762950346e-05,
+      "loss": 1.1396,
+      "step": 48
+    },
+    {
+      "epoch": 0.38811881188118813,
+      "grad_norm": 1.1638152394745782,
+      "learning_rate": 1.994839124582806e-05,
+      "loss": 1.1117,
+      "step": 49
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.7261236266090463,
+      "learning_rate": 1.993859136895274e-05,
+      "loss": 1.0745,
+      "step": 50
+    },
+    {
+      "epoch": 0.403960396039604,
+      "grad_norm": 0.6556537970861287,
+      "learning_rate": 1.9927942969004493e-05,
+      "loss": 1.0783,
+      "step": 51
+    },
+    {
+      "epoch": 0.41188118811881186,
+      "grad_norm": 1.0338775189848177,
+      "learning_rate": 1.991644695510743e-05,
+      "loss": 1.1053,
+      "step": 52
+    },
+    {
+      "epoch": 0.4198019801980198,
+      "grad_norm": 0.5045982803365276,
+      "learning_rate": 1.9904104308752053e-05,
+      "loss": 1.1187,
+      "step": 53
+    },
+    {
+      "epoch": 0.4277227722772277,
+      "grad_norm": 0.8811507158721841,
+      "learning_rate": 1.9890916083711463e-05,
+      "loss": 1.0666,
+      "step": 54
+    },
+    {
+      "epoch": 0.43564356435643564,
+      "grad_norm": 0.7323789997357792,
+      "learning_rate": 1.9876883405951378e-05,
+      "loss": 1.0613,
+      "step": 55
+    },
+    {
+      "epoch": 0.44356435643564357,
+      "grad_norm": 0.43382558782064967,
+      "learning_rate": 1.9862007473534026e-05,
+      "loss": 1.0946,
+      "step": 56
+    },
+    {
+      "epoch": 0.4514851485148515,
+      "grad_norm": 0.7855920569177011,
+      "learning_rate": 1.9846289556515835e-05,
+      "loss": 1.0801,
+      "step": 57
+    },
+    {
+      "epoch": 0.4594059405940594,
+      "grad_norm": 0.5060051358313292,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 1.0559,
+      "step": 58
+    },
+    {
+      "epoch": 0.46732673267326735,
+      "grad_norm": 0.6612232058281015,
+      "learning_rate": 1.981233320821699e-05,
+      "loss": 1.0684,
+      "step": 59
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.6407758050553994,
+      "learning_rate": 1.979409767601366e-05,
+      "loss": 1.0392,
+      "step": 60
+    },
+    {
+      "epoch": 0.48316831683168315,
+      "grad_norm": 0.4238055278476331,
+      "learning_rate": 1.9775025957116657e-05,
+      "loss": 1.0852,
+      "step": 61
+    },
+    {
+      "epoch": 0.4910891089108911,
+      "grad_norm": 0.6366553572873023,
+      "learning_rate": 1.975511967980437e-05,
+      "loss": 1.0718,
+      "step": 62
+    },
+    {
+      "epoch": 0.499009900990099,
+      "grad_norm": 0.4560763634964661,
+      "learning_rate": 1.9734380543606932e-05,
+      "loss": 1.0491,
+      "step": 63
+    },
+    {
+      "epoch": 0.5069306930693069,
+      "grad_norm": 0.47744475456040364,
+      "learning_rate": 1.971281031916114e-05,
+      "loss": 1.0682,
+      "step": 64
+    },
+    {
+      "epoch": 0.5148514851485149,
+      "grad_norm": 0.6139591331770152,
+      "learning_rate": 1.9690410848059278e-05,
+      "loss": 1.0859,
+      "step": 65
+    },
+    {
+      "epoch": 0.5227722772277228,
+      "grad_norm": 0.4633776390020583,
+      "learning_rate": 1.9667184042691877e-05,
+      "loss": 1.0637,
+      "step": 66
+    },
+    {
+      "epoch": 0.5306930693069307,
+      "grad_norm": 0.48132534481018163,
+      "learning_rate": 1.964313188608445e-05,
+      "loss": 1.1127,
+      "step": 67
+    },
+    {
+      "epoch": 0.5386138613861386,
+      "grad_norm": 0.5078593046327664,
+      "learning_rate": 1.961825643172819e-05,
+      "loss": 1.0666,
+      "step": 68
+    },
+    {
+      "epoch": 0.5465346534653466,
+      "grad_norm": 0.4641018705804529,
+      "learning_rate": 1.9592559803404652e-05,
+      "loss": 1.0412,
+      "step": 69
+    },
+    {
+      "epoch": 0.5544554455445545,
+      "grad_norm": 0.4477782377674348,
+      "learning_rate": 1.956604419500441e-05,
+      "loss": 1.0319,
+      "step": 70
+    },
+    {
+      "epoch": 0.5623762376237624,
+      "grad_norm": 0.4399022823054154,
+      "learning_rate": 1.953871187033978e-05,
+      "loss": 1.0433,
+      "step": 71
+    },
+    {
+      "epoch": 0.5702970297029702,
+      "grad_norm": 0.49392160981903666,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 1.063,
+      "step": 72
+    },
+    {
+      "epoch": 0.5782178217821782,
+      "grad_norm": 0.47294899191298795,
+      "learning_rate": 1.948160647590966e-05,
+      "loss": 1.0749,
+      "step": 73
+    },
+    {
+      "epoch": 0.5861386138613861,
+      "grad_norm": 0.41344043915965834,
+      "learning_rate": 1.94518382816082e-05,
+      "loss": 1.0979,
+      "step": 74
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.5011686560663466,
+      "learning_rate": 1.9421263121554163e-05,
+      "loss": 1.015,
+      "step": 75
+    },
+    {
+      "epoch": 0.601980198019802,
+      "grad_norm": 0.39582414491214485,
+      "learning_rate": 1.938988360615057e-05,
+      "loss": 1.0383,
+      "step": 76
+    },
+    {
+      "epoch": 0.6099009900990099,
+      "grad_norm": 0.48768604319919506,
+      "learning_rate": 1.9357702414473528e-05,
+      "loss": 1.0526,
+      "step": 77
+    },
+    {
+      "epoch": 0.6178217821782178,
+      "grad_norm": 0.45230653840089824,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 1.0308,
+      "step": 78
+    },
+    {
+      "epoch": 0.6257425742574257,
+      "grad_norm": 0.4138418438484353,
+      "learning_rate": 1.9290946060590992e-05,
+      "loss": 1.0532,
+      "step": 79
+    },
+    {
+      "epoch": 0.6336633663366337,
+      "grad_norm": 0.4370072818318615,
+      "learning_rate": 1.9256376597815565e-05,
+      "loss": 1.0673,
+      "step": 80
+    },
+    {
+      "epoch": 0.6415841584158416,
+      "grad_norm": 0.39792387068550145,
+      "learning_rate": 1.9221016857140244e-05,
+      "loss": 1.0101,
+      "step": 81
+    },
+    {
+      "epoch": 0.6495049504950495,
+      "grad_norm": 0.5007989711284164,
+      "learning_rate": 1.9184869857459233e-05,
+      "loss": 1.012,
+      "step": 82
+    },
+    {
+      "epoch": 0.6574257425742575,
+      "grad_norm": 0.4103210495096538,
+      "learning_rate": 1.9147938684880213e-05,
+      "loss": 1.0374,
+      "step": 83
+    },
+    {
+      "epoch": 0.6653465346534654,
+      "grad_norm": 0.4872855085217254,
+      "learning_rate": 1.9110226492460886e-05,
+      "loss": 1.0859,
+      "step": 84
+    },
+    {
+      "epoch": 0.6732673267326733,
+      "grad_norm": 0.422627898101724,
+      "learning_rate": 1.9071736499939765e-05,
+      "loss": 1.0518,
+      "step": 85
+    },
+    {
+      "epoch": 0.6811881188118812,
+      "grad_norm": 0.41564147530018053,
+      "learning_rate": 1.903247199346129e-05,
+      "loss": 1.0178,
+      "step": 86
+    },
+    {
+      "epoch": 0.689108910891089,
+      "grad_norm": 0.4358424246570489,
+      "learning_rate": 1.8992436325295258e-05,
+      "loss": 1.0677,
+      "step": 87
+    },
+    {
+      "epoch": 0.697029702970297,
+      "grad_norm": 0.41355898391860707,
+      "learning_rate": 1.8951632913550625e-05,
+      "loss": 1.0237,
+      "step": 88
+    },
+    {
+      "epoch": 0.7049504950495049,
+      "grad_norm": 0.3823609847824327,
+      "learning_rate": 1.891006524188368e-05,
+      "loss": 0.9833,
+      "step": 89
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 0.39209473964132163,
+      "learning_rate": 1.886773685920062e-05,
+      "loss": 1.0451,
+      "step": 90
+    },
+    {
+      "epoch": 0.7207920792079208,
+      "grad_norm": 0.4140041300883924,
+      "learning_rate": 1.882465137935456e-05,
+      "loss": 1.0222,
+      "step": 91
+    },
+    {
+      "epoch": 0.7287128712871287,
+      "grad_norm": 0.40375021194700533,
+      "learning_rate": 1.878081248083698e-05,
+      "loss": 1.0952,
+      "step": 92
+    },
+    {
+      "epoch": 0.7366336633663366,
+      "grad_norm": 0.4414196189759205,
+      "learning_rate": 1.8736223906463698e-05,
+      "loss": 1.0156,
+      "step": 93
+    },
+    {
+      "epoch": 0.7445544554455445,
+      "grad_norm": 0.4386744025847356,
+      "learning_rate": 1.8690889463055285e-05,
+      "loss": 1.0279,
+      "step": 94
+    },
+    {
+      "epoch": 0.7524752475247525,
+      "grad_norm": 0.7947840810413794,
+      "learning_rate": 1.864481302111208e-05,
+      "loss": 1.0593,
+      "step": 95
+    },
+    {
+      "epoch": 0.7603960396039604,
+      "grad_norm": 0.42527281294211106,
+      "learning_rate": 1.8597998514483724e-05,
+      "loss": 1.0055,
+      "step": 96
+    },
+    {
+      "epoch": 0.7683168316831683,
+      "grad_norm": 0.44600952063933513,
+      "learning_rate": 1.855044994003331e-05,
+      "loss": 1.0189,
+      "step": 97
+    },
+    {
+      "epoch": 0.7762376237623763,
+      "grad_norm": 0.41381659543669813,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 1.0385,
+      "step": 98
+    },
+    {
+      "epoch": 0.7841584158415842,
+      "grad_norm": 0.4356737265816363,
+      "learning_rate": 1.845316688813314e-05,
+      "loss": 1.0188,
+      "step": 99
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.3910640622588359,
+      "learning_rate": 1.840344071637893e-05,
+      "loss": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.5929595435725368,
+      "learning_rate": 1.8352997087484657e-05,
+      "loss": 1.0768,
+      "step": 101
+    },
+    {
+      "epoch": 0.807920792079208,
+      "grad_norm": 0.39724371010118187,
+      "learning_rate": 1.8301840308155507e-05,
+      "loss": 1.0546,
+      "step": 102
+    },
+    {
+      "epoch": 0.8158415841584158,
+      "grad_norm": 0.3924179902332133,
+      "learning_rate": 1.8249974745983023e-05,
+      "loss": 1.0163,
+      "step": 103
+    },
+    {
+      "epoch": 0.8237623762376237,
+      "grad_norm": 0.4531863562551441,
+      "learning_rate": 1.8197404829072214e-05,
+      "loss": 1.0125,
+      "step": 104
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 0.44574269385841797,
+      "learning_rate": 1.8144135045663486e-05,
+      "loss": 1.0399,
+      "step": 105
+    },
+    {
+      "epoch": 0.8396039603960396,
+      "grad_norm": 0.3994623879554383,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.0103,
+      "step": 106
+    },
+    {
+      "epoch": 0.8475247524752475,
+      "grad_norm": 0.41462016834859783,
+      "learning_rate": 1.8035514130686737e-05,
+      "loss": 1.0474,
+      "step": 107
+    },
+    {
+      "epoch": 0.8554455445544554,
+      "grad_norm": 0.44011181806180777,
+      "learning_rate": 1.7980172272802398e-05,
+      "loss": 1.0274,
+      "step": 108
+    },
+    {
+      "epoch": 0.8633663366336634,
+      "grad_norm": 0.4581477822740845,
+      "learning_rate": 1.792414909499574e-05,
+      "loss": 1.0291,
+      "step": 109
+    },
+    {
+      "epoch": 0.8712871287128713,
+      "grad_norm": 0.3880729293901145,
+      "learning_rate": 1.7867449380334834e-05,
+      "loss": 1.0304,
+      "step": 110
+    },
+    {
+      "epoch": 0.8792079207920792,
+      "grad_norm": 0.3756477226180992,
+      "learning_rate": 1.7810077969648157e-05,
+      "loss": 0.9737,
+      "step": 111
+    },
+    {
+      "epoch": 0.8871287128712871,
+      "grad_norm": 0.38501494156072325,
+      "learning_rate": 1.77520397611113e-05,
+      "loss": 1.0222,
+      "step": 112
+    },
+    {
+      "epoch": 0.8950495049504951,
+      "grad_norm": 0.3812791473176217,
+      "learning_rate": 1.769333970982879e-05,
+      "loss": 1.0568,
+      "step": 113
+    },
+    {
+      "epoch": 0.902970297029703,
+      "grad_norm": 0.38636764366182014,
+      "learning_rate": 1.763398282741103e-05,
+      "loss": 1.0556,
+      "step": 114
+    },
+    {
+      "epoch": 0.9108910891089109,
+      "grad_norm": 0.3689101295336194,
+      "learning_rate": 1.757397418154643e-05,
+      "loss": 1.0143,
+      "step": 115
+    },
+    {
+      "epoch": 0.9188118811881189,
+      "grad_norm": 0.36527609469057676,
+      "learning_rate": 1.7513318895568734e-05,
+      "loss": 0.9986,
+      "step": 116
+    },
+    {
+      "epoch": 0.9267326732673268,
+      "grad_norm": 0.3986163851527506,
+      "learning_rate": 1.7452022148019626e-05,
+      "loss": 1.0462,
+      "step": 117
+    },
+    {
+      "epoch": 0.9346534653465347,
+      "grad_norm": 0.37735673327905117,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 1.0072,
+      "step": 118
+    },
+    {
+      "epoch": 0.9425742574257425,
+      "grad_norm": 0.37706765852085494,
+      "learning_rate": 1.7327525255756118e-05,
+      "loss": 1.0323,
+      "step": 119
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.39377310916431657,
+      "learning_rate": 1.7264335740162244e-05,
+      "loss": 1.0422,
+      "step": 120
+    },
+    {
+      "epoch": 0.9584158415841584,
+      "grad_norm": 0.41314537071793267,
+      "learning_rate": 1.720052602033055e-05,
+      "loss": 0.9771,
+      "step": 121
+    },
+    {
+      "epoch": 0.9663366336633663,
+      "grad_norm": 0.37875715597090986,
+      "learning_rate": 1.7136101544117526e-05,
+      "loss": 0.9968,
+      "step": 122
+    },
+    {
+      "epoch": 0.9742574257425742,
+      "grad_norm": 0.37159716453417896,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.0158,
+      "step": 123
+    },
+    {
+      "epoch": 0.9821782178217822,
+      "grad_norm": 0.36633287049364816,
+      "learning_rate": 1.700543037593291e-05,
+      "loss": 1.0113,
+      "step": 124
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.3639299308468012,
+      "learning_rate": 1.6939194840220497e-05,
+      "loss": 1.0108,
+      "step": 125
+    },
+    {
+      "epoch": 0.998019801980198,
+      "grad_norm": 0.3687515525421076,
+      "learning_rate": 1.687236685969263e-05,
+      "loss": 1.0183,
+      "step": 126
+    },
+    {
+      "epoch": 0.998019801980198,
+      "eval_loss": 1.0126549005508423,
+      "eval_runtime": 87.7583,
+      "eval_samples_per_second": 3.031,
+      "eval_steps_per_second": 0.194,
+      "step": 126
+    },
+    {
+      "epoch": 1.005940594059406,
+      "grad_norm": 0.6033515169314877,
+      "learning_rate": 1.6804952139894618e-05,
+      "loss": 0.9244,
+      "step": 127
+    },
+    {
+      "epoch": 1.0138613861386139,
+      "grad_norm": 0.5458375892374859,
+      "learning_rate": 1.6736956436465573e-05,
+      "loss": 0.8684,
+      "step": 128
+    },
+    {
+      "epoch": 1.0217821782178218,
+      "grad_norm": 0.6652946196593673,
+      "learning_rate": 1.6668385554647017e-05,
+      "loss": 0.8744,
+      "step": 129
+    },
+    {
+      "epoch": 1.0297029702970297,
+      "grad_norm": 0.47420107863397504,
+      "learning_rate": 1.659924534878723e-05,
+      "loss": 0.8562,
+      "step": 130
+    },
+    {
+      "epoch": 1.0376237623762377,
+      "grad_norm": 0.6395196023840517,
+      "learning_rate": 1.6529541721841444e-05,
+      "loss": 0.8653,
+      "step": 131
+    },
+    {
+      "epoch": 1.0455445544554456,
+      "grad_norm": 0.49490432639088666,
+      "learning_rate": 1.6459280624867876e-05,
+      "loss": 0.8939,
+      "step": 132
+    },
+    {
+      "epoch": 1.0534653465346535,
+      "grad_norm": 0.662156431335598,
+      "learning_rate": 1.638846805651961e-05,
+      "loss": 0.8772,
+      "step": 133
+    },
+    {
+      "epoch": 1.0613861386138614,
+      "grad_norm": 0.4315607187688008,
+      "learning_rate": 1.631711006253251e-05,
+      "loss": 0.8719,
+      "step": 134
+    },
+    {
+      "epoch": 1.0693069306930694,
+      "grad_norm": 0.5428981275030659,
+      "learning_rate": 1.6245212735208994e-05,
+      "loss": 0.8902,
+      "step": 135
+    },
+    {
+      "epoch": 1.0772277227722773,
+      "grad_norm": 0.4212431283579326,
+      "learning_rate": 1.617278221289793e-05,
+      "loss": 0.8958,
+      "step": 136
+    },
+    {
+      "epoch": 1.0851485148514852,
+      "grad_norm": 0.45956779312336216,
+      "learning_rate": 1.609982467947057e-05,
+      "loss": 0.8798,
+      "step": 137
+    },
+    {
+      "epoch": 1.0930693069306932,
+      "grad_norm": 0.5318677463313782,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 0.8691,
+      "step": 138
+    },
+    {
+      "epoch": 1.100990099009901,
+      "grad_norm": 0.420504194389614,
+      "learning_rate": 1.595235353919219e-05,
+      "loss": 0.8711,
+      "step": 139
+    },
+    {
+      "epoch": 1.108910891089109,
+      "grad_norm": 0.4826547764308898,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 0.8908,
+      "step": 140
+    },
+    {
+      "epoch": 1.116831683168317,
+      "grad_norm": 0.3992971335438903,
+      "learning_rate": 1.580284967563316e-05,
+      "loss": 0.8591,
+      "step": 141
+    },
+    {
+      "epoch": 1.1247524752475249,
+      "grad_norm": 0.4402406328520412,
+      "learning_rate": 1.5727351400805054e-05,
+      "loss": 0.839,
+      "step": 142
+    },
+    {
+      "epoch": 1.1326732673267328,
+      "grad_norm": 0.41454275441137073,
+      "learning_rate": 1.565136414422592e-05,
+      "loss": 0.8566,
+      "step": 143
+    },
+    {
+      "epoch": 1.1405940594059407,
+      "grad_norm": 0.4296709034986113,
+      "learning_rate": 1.5574894393428856e-05,
+      "loss": 0.8881,
+      "step": 144
+    },
+    {
+      "epoch": 1.1485148514851484,
+      "grad_norm": 0.45117629451958274,
+      "learning_rate": 1.5497948677140673e-05,
+      "loss": 0.8457,
+      "step": 145
+    },
+    {
+      "epoch": 1.1564356435643564,
+      "grad_norm": 0.3989063232783904,
+      "learning_rate": 1.5420533564724495e-05,
+      "loss": 0.8805,
+      "step": 146
+    },
+    {
+      "epoch": 1.1643564356435643,
+      "grad_norm": 0.44568328942669366,
+      "learning_rate": 1.5342655665618885e-05,
+      "loss": 0.853,
+      "step": 147
+    },
+    {
+      "epoch": 1.1722772277227722,
+      "grad_norm": 0.39828075995328915,
+      "learning_rate": 1.526432162877356e-05,
+      "loss": 0.8831,
+      "step": 148
+    },
+    {
+      "epoch": 1.1801980198019801,
+      "grad_norm": 0.41294672710780717,
+      "learning_rate": 1.5185538142081721e-05,
+      "loss": 0.8786,
+      "step": 149
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.40873959614869637,
+      "learning_rate": 1.510631193180907e-05,
+      "loss": 0.8684,
+      "step": 150
+    },
+    {
+      "epoch": 1.196039603960396,
+      "grad_norm": 0.3978636394954677,
+      "learning_rate": 1.5026649762019539e-05,
+      "loss": 0.8756,
+      "step": 151
+    },
+    {
+      "epoch": 1.203960396039604,
+      "grad_norm": 0.5036601026033098,
+      "learning_rate": 1.4946558433997792e-05,
+      "loss": 0.844,
+      "step": 152
+    },
+    {
+      "epoch": 1.2118811881188118,
+      "grad_norm": 0.3932657455702579,
+      "learning_rate": 1.4866044785668563e-05,
+      "loss": 0.801,
+      "step": 153
+    },
+    {
+      "epoch": 1.2198019801980198,
+      "grad_norm": 0.41396973144650107,
+      "learning_rate": 1.4785115691012866e-05,
+      "loss": 0.8854,
+      "step": 154
+    },
+    {
+      "epoch": 1.2277227722772277,
+      "grad_norm": 0.4095963357893977,
+      "learning_rate": 1.4703778059481096e-05,
+      "loss": 0.8629,
+      "step": 155
+    },
+    {
+      "epoch": 1.2356435643564356,
+      "grad_norm": 0.3844996926085625,
+      "learning_rate": 1.4622038835403135e-05,
+      "loss": 0.8802,
+      "step": 156
+    },
+    {
+      "epoch": 1.2435643564356436,
+      "grad_norm": 0.38098631899426383,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 0.8546,
+      "step": 157
+    },
+    {
+      "epoch": 1.2514851485148515,
+      "grad_norm": 0.38645301150023,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.8745,
+      "step": 158
+    },
+    {
+      "epoch": 1.2594059405940594,
+      "grad_norm": 0.38284619702545075,
+      "learning_rate": 1.4374481561912266e-05,
+      "loss": 0.8618,
+      "step": 159
+    },
+    {
+      "epoch": 1.2673267326732673,
+      "grad_norm": 0.4209251000095392,
+      "learning_rate": 1.429120608772609e-05,
+      "loss": 0.8839,
+      "step": 160
+    },
+    {
+      "epoch": 1.2752475247524753,
+      "grad_norm": 0.402410646316122,
+      "learning_rate": 1.4207564244983154e-05,
+      "loss": 0.8741,
+      "step": 161
+    },
+    {
+      "epoch": 1.2831683168316832,
+      "grad_norm": 0.39477095820040203,
+      "learning_rate": 1.4123563174739036e-05,
+      "loss": 0.8883,
+      "step": 162
+    },
+    {
+      "epoch": 1.2910891089108911,
+      "grad_norm": 0.3924015414958881,
+      "learning_rate": 1.403921004871895e-05,
+      "loss": 0.8576,
+      "step": 163
+    },
+    {
+      "epoch": 1.299009900990099,
+      "grad_norm": 0.4161025068008364,
+      "learning_rate": 1.3954512068705425e-05,
+      "loss": 0.8305,
+      "step": 164
+    },
+    {
+      "epoch": 1.306930693069307,
+      "grad_norm": 0.4263635509257888,
+      "learning_rate": 1.3869476465923455e-05,
+      "loss": 0.8647,
+      "step": 165
+    },
+    {
+      "epoch": 1.314851485148515,
+      "grad_norm": 0.39404329089929485,
+      "learning_rate": 1.3784110500423104e-05,
+      "loss": 0.8622,
+      "step": 166
+    },
+    {
+      "epoch": 1.3227722772277228,
+      "grad_norm": 0.3805109485657045,
+      "learning_rate": 1.3698421460459692e-05,
+      "loss": 0.862,
+      "step": 167
+    },
+    {
+      "epoch": 1.3306930693069308,
+      "grad_norm": 0.40690294201503635,
+      "learning_rate": 1.3612416661871532e-05,
+      "loss": 0.8647,
+      "step": 168
+    },
+    {
+      "epoch": 1.3386138613861387,
+      "grad_norm": 0.4259562065252122,
+      "learning_rate": 1.3526103447455326e-05,
+      "loss": 0.8563,
+      "step": 169
+    },
+    {
+      "epoch": 1.3465346534653464,
+      "grad_norm": 0.3810965967304589,
+      "learning_rate": 1.3439489186339283e-05,
+      "loss": 0.8311,
+      "step": 170
+    },
+    {
+      "epoch": 1.3544554455445543,
+      "grad_norm": 0.39136590416953965,
+      "learning_rate": 1.335258127335394e-05,
+      "loss": 0.8471,
+      "step": 171
+    },
+    {
+      "epoch": 1.3623762376237623,
+      "grad_norm": 0.41483855969298006,
+      "learning_rate": 1.3265387128400833e-05,
+      "loss": 0.8609,
+      "step": 172
+    },
+    {
+      "epoch": 1.3702970297029702,
+      "grad_norm": 0.40516699447727095,
+      "learning_rate": 1.3177914195819018e-05,
+      "loss": 0.8275,
+      "step": 173
+    },
+    {
+      "epoch": 1.378217821782178,
+      "grad_norm": 0.4793820142436531,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.8749,
+      "step": 174
+    },
+    {
+      "epoch": 1.386138613861386,
+      "grad_norm": 0.3840703344721545,
+      "learning_rate": 1.3002161863497529e-05,
+      "loss": 0.8966,
+      "step": 175
+    },
+    {
+      "epoch": 1.394059405940594,
+      "grad_norm": 0.41308469917146595,
+      "learning_rate": 1.2913897468893249e-05,
+      "loss": 0.8914,
+      "step": 176
+    },
+    {
+      "epoch": 1.401980198019802,
+      "grad_norm": 0.3827637794217713,
+      "learning_rate": 1.2825384295649952e-05,
+      "loss": 0.8299,
+      "step": 177
+    },
+    {
+      "epoch": 1.4099009900990098,
+      "grad_norm": 0.4492756954997741,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.8736,
+      "step": 178
+    },
+    {
+      "epoch": 1.4178217821782177,
+      "grad_norm": 0.3770575870144539,
+      "learning_rate": 1.2647641861653759e-05,
+      "loss": 0.8602,
+      "step": 179
+    },
+    {
+      "epoch": 1.4257425742574257,
+      "grad_norm": 0.3900899921685637,
+      "learning_rate": 1.2558427775944357e-05,
+      "loss": 0.8365,
+      "step": 180
+    },
+    {
+      "epoch": 1.4336633663366336,
+      "grad_norm": 0.41840094530944894,
+      "learning_rate": 1.2468995260387332e-05,
+      "loss": 0.8993,
+      "step": 181
+    },
+    {
+      "epoch": 1.4415841584158415,
+      "grad_norm": 0.40583158631957733,
+      "learning_rate": 1.2379351950426188e-05,
+      "loss": 0.8691,
+      "step": 182
+    },
+    {
+      "epoch": 1.4495049504950495,
+      "grad_norm": 0.3966569139417299,
+      "learning_rate": 1.2289505499501341e-05,
+      "loss": 0.8711,
+      "step": 183
+    },
+    {
+      "epoch": 1.4574257425742574,
+      "grad_norm": 0.41194466483513786,
+      "learning_rate": 1.2199463578396688e-05,
+      "loss": 0.8338,
+      "step": 184
+    },
+    {
+      "epoch": 1.4653465346534653,
+      "grad_norm": 0.3818733353460163,
+      "learning_rate": 1.21092338745847e-05,
+      "loss": 0.8403,
+      "step": 185
+    },
+    {
+      "epoch": 1.4732673267326732,
+      "grad_norm": 0.48110222651862666,
+      "learning_rate": 1.2018824091570103e-05,
+      "loss": 0.8359,
+      "step": 186
+    },
+    {
+      "epoch": 1.4811881188118812,
+      "grad_norm": 0.39846082622633,
+      "learning_rate": 1.192824194823217e-05,
+      "loss": 0.8862,
+      "step": 187
+    },
+    {
+      "epoch": 1.489108910891089,
+      "grad_norm": 0.4794826007648338,
+      "learning_rate": 1.1837495178165706e-05,
+      "loss": 0.8611,
+      "step": 188
+    },
+    {
+      "epoch": 1.497029702970297,
+      "grad_norm": 0.41925943616423056,
+      "learning_rate": 1.1746591529020789e-05,
+      "loss": 0.8734,
+      "step": 189
+    },
+    {
+      "epoch": 1.504950495049505,
+      "grad_norm": 0.40682041747226527,
+      "learning_rate": 1.16555387618413e-05,
+      "loss": 0.85,
+      "step": 190
+    },
+    {
+      "epoch": 1.5128712871287129,
+      "grad_norm": 0.3925259196133537,
+      "learning_rate": 1.156434465040231e-05,
+      "loss": 0.8685,
+      "step": 191
+    },
+    {
+      "epoch": 1.5207920792079208,
+      "grad_norm": 0.3917596296811381,
+      "learning_rate": 1.1473016980546377e-05,
+      "loss": 0.8613,
+      "step": 192
+    },
+    {
+      "epoch": 1.5287128712871287,
+      "grad_norm": 0.3916872938793011,
+      "learning_rate": 1.1381563549518823e-05,
+      "loss": 0.8708,
+      "step": 193
+    },
+    {
+      "epoch": 1.5366336633663367,
+      "grad_norm": 0.4079178768846547,
+      "learning_rate": 1.1289992165302036e-05,
+      "loss": 0.8444,
+      "step": 194
+    },
+    {
+      "epoch": 1.5445544554455446,
+      "grad_norm": 0.4239468808643011,
+      "learning_rate": 1.1198310645948833e-05,
+      "loss": 0.8475,
+      "step": 195
+    },
+    {
+      "epoch": 1.5524752475247525,
+      "grad_norm": 0.4143090508458373,
+      "learning_rate": 1.1106526818915008e-05,
+      "loss": 0.8584,
+      "step": 196
+    },
+    {
+      "epoch": 1.5603960396039604,
+      "grad_norm": 0.3749410819598408,
+      "learning_rate": 1.1014648520391031e-05,
+      "loss": 0.8694,
+      "step": 197
+    },
+    {
+      "epoch": 1.5683168316831684,
+      "grad_norm": 0.38698513255681644,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.8895,
+      "step": 198
+    },
+    {
+      "epoch": 1.5762376237623763,
+      "grad_norm": 0.3945257947528202,
+      "learning_rate": 1.083063989329304e-05,
+      "loss": 0.8437,
+      "step": 199
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 0.38726772534551934,
+      "learning_rate": 1.073852527474874e-05,
+      "loss": 0.9063,
+      "step": 200
+    },
+    {
+      "epoch": 1.5920792079207922,
+      "grad_norm": 0.3806123804826243,
+      "learning_rate": 1.0646347603432443e-05,
+      "loss": 0.8432,
+      "step": 201
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.39146660949081974,
+      "learning_rate": 1.05541147491597e-05,
+      "loss": 0.8676,
+      "step": 202
+    },
+    {
+      "epoch": 1.607920792079208,
+      "grad_norm": 0.3845422288308008,
+      "learning_rate": 1.0461834586457398e-05,
+      "loss": 0.852,
+      "step": 203
+    },
+    {
+      "epoch": 1.615841584158416,
+      "grad_norm": 0.3854898725988794,
+      "learning_rate": 1.0369514993891451e-05,
+      "loss": 0.8376,
+      "step": 204
+    },
+    {
+      "epoch": 1.6237623762376239,
+      "grad_norm": 0.40353321866721364,
+      "learning_rate": 1.0277163853394166e-05,
+      "loss": 0.852,
+      "step": 205
+    },
+    {
+      "epoch": 1.6316831683168318,
+      "grad_norm": 0.38444130174939833,
+      "learning_rate": 1.01847890495913e-05,
+      "loss": 0.889,
+      "step": 206
+    },
+    {
+      "epoch": 1.6396039603960397,
+      "grad_norm": 0.38108640413144107,
+      "learning_rate": 1.009239846912891e-05,
+      "loss": 0.8359,
+      "step": 207
+    },
+    {
+      "epoch": 1.6475247524752477,
+      "grad_norm": 0.4747347151817832,
+      "learning_rate": 1e-05,
+      "loss": 0.8865,
+      "step": 208
+    },
+    {
+      "epoch": 1.6554455445544556,
+      "grad_norm": 0.40452870424857584,
+      "learning_rate": 9.907601530871094e-06,
+      "loss": 0.8253,
+      "step": 209
+    },
+    {
+      "epoch": 1.6633663366336635,
+      "grad_norm": 0.38987399344119467,
+      "learning_rate": 9.815210950408703e-06,
+      "loss": 0.849,
+      "step": 210
+    },
+    {
+      "epoch": 1.6712871287128714,
+      "grad_norm": 0.39493082174252364,
+      "learning_rate": 9.722836146605838e-06,
+      "loss": 0.8483,
+      "step": 211
+    },
+    {
+      "epoch": 1.6792079207920794,
+      "grad_norm": 0.39165994965141043,
+      "learning_rate": 9.630485006108554e-06,
+      "loss": 0.8871,
+      "step": 212
+    },
+    {
+      "epoch": 1.6871287128712873,
+      "grad_norm": 0.38092018061735106,
+      "learning_rate": 9.538165413542607e-06,
+      "loss": 0.8518,
+      "step": 213
+    },
+    {
+      "epoch": 1.695049504950495,
+      "grad_norm": 0.3855485261645927,
+      "learning_rate": 9.445885250840301e-06,
+      "loss": 0.8356,
+      "step": 214
+    },
+    {
+      "epoch": 1.702970297029703,
+      "grad_norm": 0.39414553727691437,
+      "learning_rate": 9.353652396567558e-06,
+      "loss": 0.8689,
+      "step": 215
+    },
+    {
+      "epoch": 1.7108910891089109,
+      "grad_norm": 0.383608920878984,
+      "learning_rate": 9.261474725251261e-06,
+      "loss": 0.8462,
+      "step": 216
+    },
+    {
+      "epoch": 1.7188118811881188,
+      "grad_norm": 0.37956984957800455,
+      "learning_rate": 9.169360106706962e-06,
+      "loss": 0.8636,
+      "step": 217
+    },
+    {
+      "epoch": 1.7267326732673267,
+      "grad_norm": 0.3952521158053759,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.8371,
+      "step": 218
+    },
+    {
+      "epoch": 1.7346534653465346,
+      "grad_norm": 0.39432968092671433,
+      "learning_rate": 8.985351479608972e-06,
+      "loss": 0.8686,
+      "step": 219
+    },
+    {
+      "epoch": 1.7425742574257426,
+      "grad_norm": 0.4091695075116408,
+      "learning_rate": 8.893473181084993e-06,
+      "loss": 0.8854,
+      "step": 220
+    },
+    {
+      "epoch": 1.7504950495049505,
+      "grad_norm": 0.38879198281346644,
+      "learning_rate": 8.80168935405117e-06,
+      "loss": 0.8258,
+      "step": 221
+    },
+    {
+      "epoch": 1.7584158415841584,
+      "grad_norm": 0.3787674450951966,
+      "learning_rate": 8.71000783469797e-06,
+      "loss": 0.8577,
+      "step": 222
+    },
+    {
+      "epoch": 1.7663366336633664,
+      "grad_norm": 0.4140574481556825,
+      "learning_rate": 8.618436450481182e-06,
+      "loss": 0.8717,
+      "step": 223
+    },
+    {
+      "epoch": 1.7742574257425743,
+      "grad_norm": 0.3816315351422027,
+      "learning_rate": 8.526983019453624e-06,
+      "loss": 0.8328,
+      "step": 224
+    },
+    {
+      "epoch": 1.7821782178217822,
+      "grad_norm": 0.3778129363378664,
+      "learning_rate": 8.43565534959769e-06,
+      "loss": 0.8625,
+      "step": 225
+    },
+    {
+      "epoch": 1.7900990099009901,
+      "grad_norm": 0.39307248999316513,
+      "learning_rate": 8.3444612381587e-06,
+      "loss": 0.8472,
+      "step": 226
+    },
+    {
+      "epoch": 1.798019801980198,
+      "grad_norm": 0.567116321231214,
+      "learning_rate": 8.253408470979212e-06,
+      "loss": 0.8435,
+      "step": 227
+    },
+    {
+      "epoch": 1.805940594059406,
+      "grad_norm": 0.3826967696218752,
+      "learning_rate": 8.162504821834296e-06,
+      "loss": 0.8287,
+      "step": 228
+    },
+    {
+      "epoch": 1.8138613861386137,
+      "grad_norm": 0.4031524752294553,
+      "learning_rate": 8.071758051767833e-06,
+      "loss": 0.8372,
+      "step": 229
+    },
+    {
+      "epoch": 1.8217821782178216,
+      "grad_norm": 0.38474330971078624,
+      "learning_rate": 7.9811759084299e-06,
+      "loss": 0.8722,
+      "step": 230
+    },
+    {
+      "epoch": 1.8297029702970296,
+      "grad_norm": 0.3835735801490187,
+      "learning_rate": 7.890766125415304e-06,
+      "loss": 0.9066,
+      "step": 231
+    },
+    {
+      "epoch": 1.8376237623762375,
+      "grad_norm": 0.4060540049015593,
+      "learning_rate": 7.800536421603317e-06,
+      "loss": 0.8252,
+      "step": 232
+    },
+    {
+      "epoch": 1.8455445544554454,
+      "grad_norm": 0.386875601730567,
+      "learning_rate": 7.710494500498662e-06,
+      "loss": 0.8643,
+      "step": 233
+    },
+    {
+      "epoch": 1.8534653465346533,
+      "grad_norm": 0.38667621959177934,
+      "learning_rate": 7.620648049573815e-06,
+      "loss": 0.857,
+      "step": 234
+    },
+    {
+      "epoch": 1.8613861386138613,
+      "grad_norm": 0.38808086535439623,
+      "learning_rate": 7.531004739612668e-06,
+      "loss": 0.846,
+      "step": 235
+    },
+    {
+      "epoch": 1.8693069306930692,
+      "grad_norm": 0.3980360267748509,
+      "learning_rate": 7.441572224055644e-06,
+      "loss": 0.8394,
+      "step": 236
+    },
+    {
+      "epoch": 1.8772277227722771,
+      "grad_norm": 0.38040890589313575,
+      "learning_rate": 7.352358138346241e-06,
+      "loss": 0.8321,
+      "step": 237
+    },
+    {
+      "epoch": 1.885148514851485,
+      "grad_norm": 0.36846374610523613,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.8497,
+      "step": 238
+    },
+    {
+      "epoch": 1.893069306930693,
+      "grad_norm": 0.3864744771519634,
+      "learning_rate": 7.17461570435005e-06,
+      "loss": 0.8568,
+      "step": 239
+    },
+    {
+      "epoch": 1.900990099009901,
+      "grad_norm": 0.4061916523025884,
+      "learning_rate": 7.086102531106755e-06,
+      "loss": 0.9014,
+      "step": 240
+    },
+    {
+      "epoch": 1.9089108910891088,
+      "grad_norm": 0.4041879159841448,
+      "learning_rate": 6.997838136502474e-06,
+      "loss": 0.8792,
+      "step": 241
+    },
+    {
+      "epoch": 1.9168316831683168,
+      "grad_norm": 0.42210348978875756,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.8597,
+      "step": 242
+    },
+    {
+      "epoch": 1.9247524752475247,
+      "grad_norm": 0.3878637842247315,
+      "learning_rate": 6.822085804180985e-06,
+      "loss": 0.889,
+      "step": 243
+    },
+    {
+      "epoch": 1.9326732673267326,
+      "grad_norm": 0.3903220656513824,
+      "learning_rate": 6.734612871599169e-06,
+      "loss": 0.8518,
+      "step": 244
+    },
+    {
+      "epoch": 1.9405940594059405,
+      "grad_norm": 0.38140916668736696,
+      "learning_rate": 6.647418726646065e-06,
+      "loss": 0.8664,
+      "step": 245
+    },
+    {
+      "epoch": 1.9485148514851485,
+      "grad_norm": 0.37076093981349967,
+      "learning_rate": 6.560510813660719e-06,
+      "loss": 0.8115,
+      "step": 246
+    },
+    {
+      "epoch": 1.9564356435643564,
+      "grad_norm": 0.38782683714399413,
+      "learning_rate": 6.473896552544674e-06,
+      "loss": 0.8616,
+      "step": 247
+    },
+    {
+      "epoch": 1.9643564356435643,
+      "grad_norm": 0.3806774040873917,
+      "learning_rate": 6.387583338128471e-06,
+      "loss": 0.8547,
+      "step": 248
+    },
+    {
+      "epoch": 1.9722772277227723,
+      "grad_norm": 0.39269059714326215,
+      "learning_rate": 6.30157853954031e-06,
+      "loss": 0.8466,
+      "step": 249
+    },
+    {
+      "epoch": 1.9801980198019802,
+      "grad_norm": 0.3887611447725159,
+      "learning_rate": 6.215889499576898e-06,
+      "loss": 0.8347,
+      "step": 250
+    },
+    {
+      "epoch": 1.988118811881188,
+      "grad_norm": 0.3776184815702374,
+      "learning_rate": 6.130523534076549e-06,
+      "loss": 0.8313,
+      "step": 251
+    },
+    {
+      "epoch": 1.996039603960396,
+      "grad_norm": 0.39378215320119175,
+      "learning_rate": 6.0454879312945755e-06,
+      "loss": 0.869,
+      "step": 252
+    },
+    {
+      "epoch": 1.996039603960396,
+      "eval_loss": 1.002571702003479,
+      "eval_runtime": 88.5175,
+      "eval_samples_per_second": 3.005,
+      "eval_steps_per_second": 0.192,
+      "step": 252
+    },
+    {
+      "epoch": 2.003960396039604,
+      "grad_norm": 0.576420587207012,
+      "learning_rate": 5.960789951281052e-06,
+      "loss": 0.7911,
+      "step": 253
+    },
+    {
+      "epoch": 2.011881188118812,
+      "grad_norm": 0.781752019713,
+      "learning_rate": 5.876436825260967e-06,
+      "loss": 0.7259,
+      "step": 254
+    },
+    {
+      "epoch": 2.01980198019802,
+      "grad_norm": 0.6274336393038759,
+      "learning_rate": 5.7924357550168534e-06,
+      "loss": 0.7553,
+      "step": 255
+    },
+    {
+      "epoch": 2.0277227722772277,
+      "grad_norm": 0.638695579314472,
+      "learning_rate": 5.708793912273911e-06,
+      "loss": 0.7508,
+      "step": 256
+    },
+    {
+      "epoch": 2.0356435643564357,
+      "grad_norm": 0.708507864502287,
+      "learning_rate": 5.625518438087738e-06,
+      "loss": 0.7477,
+      "step": 257
+    },
+    {
+      "epoch": 2.0435643564356436,
+      "grad_norm": 0.5492723143519291,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.7429,
+      "step": 258
+    },
+    {
+      "epoch": 2.0514851485148515,
+      "grad_norm": 0.6026775840172064,
+      "learning_rate": 5.460095002604533e-06,
+      "loss": 0.7175,
+      "step": 259
+    },
+    {
+      "epoch": 2.0594059405940595,
+      "grad_norm": 0.6699241593183407,
+      "learning_rate": 5.3779611645968696e-06,
+      "loss": 0.7093,
+      "step": 260
+    },
+    {
+      "epoch": 2.0673267326732674,
+      "grad_norm": 0.5343067117420846,
+      "learning_rate": 5.296221940518908e-06,
+      "loss": 0.7232,
+      "step": 261
+    },
+    {
+      "epoch": 2.0752475247524753,
+      "grad_norm": 0.4911057371956158,
+      "learning_rate": 5.214884308987136e-06,
+      "loss": 0.7802,
+      "step": 262
+    },
+    {
+      "epoch": 2.0831683168316832,
+      "grad_norm": 0.5433218831841199,
+      "learning_rate": 5.133955214331439e-06,
+      "loss": 0.7053,
+      "step": 263
+    },
+    {
+      "epoch": 2.091089108910891,
+      "grad_norm": 0.5400653655431835,
+      "learning_rate": 5.053441566002214e-06,
+      "loss": 0.7098,
+      "step": 264
+    },
+    {
+      "epoch": 2.099009900990099,
+      "grad_norm": 0.4898471275769769,
+      "learning_rate": 4.973350237980466e-06,
+      "loss": 0.739,
+      "step": 265
+    },
+    {
+      "epoch": 2.106930693069307,
+      "grad_norm": 0.4939480668131728,
+      "learning_rate": 4.893688068190933e-06,
+      "loss": 0.7255,
+      "step": 266
+    },
+    {
+      "epoch": 2.114851485148515,
+      "grad_norm": 0.5066963493135274,
+      "learning_rate": 4.814461857918279e-06,
+      "loss": 0.7502,
+      "step": 267
+    },
+    {
+      "epoch": 2.122772277227723,
+      "grad_norm": 0.5064134093537243,
+      "learning_rate": 4.7356783712264405e-06,
+      "loss": 0.7113,
+      "step": 268
+    },
+    {
+      "epoch": 2.130693069306931,
+      "grad_norm": 0.4224734666377468,
+      "learning_rate": 4.657344334381116e-06,
+      "loss": 0.7215,
+      "step": 269
+    },
+    {
+      "epoch": 2.1386138613861387,
+      "grad_norm": 0.459279750043329,
+      "learning_rate": 4.579466435275506e-06,
+      "loss": 0.7407,
+      "step": 270
+    },
+    {
+      "epoch": 2.1465346534653467,
+      "grad_norm": 0.46742630810280705,
+      "learning_rate": 4.5020513228593275e-06,
+      "loss": 0.6973,
+      "step": 271
+    },
+    {
+      "epoch": 2.1544554455445546,
+      "grad_norm": 0.4943363620760823,
+      "learning_rate": 4.425105606571145e-06,
+      "loss": 0.7338,
+      "step": 272
+    },
+    {
+      "epoch": 2.1623762376237625,
+      "grad_norm": 0.433433891249229,
+      "learning_rate": 4.348635855774082e-06,
+      "loss": 0.721,
+      "step": 273
+    },
+    {
+      "epoch": 2.1702970297029704,
+      "grad_norm": 0.44511761437854985,
+      "learning_rate": 4.272648599194948e-06,
+      "loss": 0.7183,
+      "step": 274
+    },
+    {
+      "epoch": 2.1782178217821784,
+      "grad_norm": 0.4758876220892502,
+      "learning_rate": 4.197150324366844e-06,
+      "loss": 0.6928,
+      "step": 275
+    },
+    {
+      "epoch": 2.1861386138613863,
+      "grad_norm": 0.49467814256335324,
+      "learning_rate": 4.12214747707527e-06,
+      "loss": 0.7151,
+      "step": 276
+    },
+    {
+      "epoch": 2.1940594059405942,
+      "grad_norm": 0.4332527533958727,
+      "learning_rate": 4.047646460807814e-06,
+      "loss": 0.7231,
+      "step": 277
+    },
+    {
+      "epoch": 2.201980198019802,
+      "grad_norm": 0.4341696748234564,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.7161,
+      "step": 278
+    },
+    {
+      "epoch": 2.20990099009901,
+      "grad_norm": 0.4892958618243702,
+      "learning_rate": 3.9001753205294335e-06,
+      "loss": 0.7385,
+      "step": 279
+    },
+    {
+      "epoch": 2.217821782178218,
+      "grad_norm": 0.42779412099186476,
+      "learning_rate": 3.827217787102072e-06,
+      "loss": 0.6949,
+      "step": 280
+    },
+    {
+      "epoch": 2.225742574257426,
+      "grad_norm": 0.43010675128621945,
+      "learning_rate": 3.754787264791011e-06,
+      "loss": 0.7279,
+      "step": 281
+    },
+    {
+      "epoch": 2.233663366336634,
+      "grad_norm": 0.4189623315492079,
+      "learning_rate": 3.6828899374674933e-06,
+      "loss": 0.7151,
+      "step": 282
+    },
+    {
+      "epoch": 2.241584158415842,
+      "grad_norm": 0.4283610207819412,
+      "learning_rate": 3.6115319434803897e-06,
+      "loss": 0.767,
+      "step": 283
+    },
+    {
+      "epoch": 2.2495049504950497,
+      "grad_norm": 0.4344389534943353,
+      "learning_rate": 3.540719375132129e-06,
+      "loss": 0.7271,
+      "step": 284
+    },
+    {
+      "epoch": 2.2574257425742577,
+      "grad_norm": 0.4361317858889359,
+      "learning_rate": 3.4704582781585596e-06,
+      "loss": 0.7248,
+      "step": 285
+    },
+    {
+      "epoch": 2.2653465346534656,
+      "grad_norm": 0.43728115762338654,
+      "learning_rate": 3.4007546512127764e-06,
+      "loss": 0.7231,
+      "step": 286
+    },
+    {
+      "epoch": 2.2732673267326735,
+      "grad_norm": 0.4264346314477906,
+      "learning_rate": 3.3316144453529897e-06,
+      "loss": 0.7265,
+      "step": 287
+    },
+    {
+      "epoch": 2.2811881188118814,
+      "grad_norm": 0.4328763606745891,
+      "learning_rate": 3.2630435635344283e-06,
+      "loss": 0.726,
+      "step": 288
+    },
+    {
+      "epoch": 2.289108910891089,
+      "grad_norm": 0.40543132963978806,
+      "learning_rate": 3.1950478601053847e-06,
+      "loss": 0.7226,
+      "step": 289
+    },
+    {
+      "epoch": 2.297029702970297,
+      "grad_norm": 0.40808543584405227,
+      "learning_rate": 3.1276331403073733e-06,
+      "loss": 0.6789,
+      "step": 290
+    },
+    {
+      "epoch": 2.3049504950495048,
+      "grad_norm": 0.40839769173881413,
+      "learning_rate": 3.0608051597795043e-06,
+      "loss": 0.7187,
+      "step": 291
+    },
+    {
+      "epoch": 2.3128712871287127,
+      "grad_norm": 0.4369573292307265,
+      "learning_rate": 2.9945696240670905e-06,
+      "loss": 0.7301,
+      "step": 292
+    },
+    {
+      "epoch": 2.3207920792079206,
+      "grad_norm": 0.40752917080947654,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.7371,
+      "step": 293
+    },
+    {
+      "epoch": 2.3287128712871286,
+      "grad_norm": 0.40681720921863107,
+      "learning_rate": 2.8638984558824777e-06,
+      "loss": 0.7053,
+      "step": 294
+    },
+    {
+      "epoch": 2.3366336633663365,
+      "grad_norm": 0.39704090696075117,
+      "learning_rate": 2.799473979669456e-06,
+      "loss": 0.7222,
+      "step": 295
+    },
+    {
+      "epoch": 2.3445544554455444,
+      "grad_norm": 0.4127972906314945,
+      "learning_rate": 2.7356642598377604e-06,
+      "loss": 0.7227,
+      "step": 296
+    },
+    {
+      "epoch": 2.3524752475247523,
+      "grad_norm": 0.40247162704682216,
+      "learning_rate": 2.672474744243888e-06,
+      "loss": 0.7178,
+      "step": 297
+    },
+    {
+      "epoch": 2.3603960396039603,
+      "grad_norm": 0.4070193008615235,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.7164,
+      "step": 298
+    },
+    {
+      "epoch": 2.368316831683168,
+      "grad_norm": 0.3958026290470292,
+      "learning_rate": 2.547977851980373e-06,
+      "loss": 0.7226,
+      "step": 299
+    },
+    {
+      "epoch": 2.376237623762376,
+      "grad_norm": 0.414324012823234,
+      "learning_rate": 2.4866811044312667e-06,
+      "loss": 0.722,
+      "step": 300
+    },
+    {
+      "epoch": 2.384158415841584,
+      "grad_norm": 0.3924655139400483,
+      "learning_rate": 2.426025818453572e-06,
+      "loss": 0.6922,
+      "step": 301
+    },
+    {
+      "epoch": 2.392079207920792,
+      "grad_norm": 0.39324797222146385,
+      "learning_rate": 2.3660171725889703e-06,
+      "loss": 0.7168,
+      "step": 302
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4018290113845056,
+      "learning_rate": 2.306660290171211e-06,
+      "loss": 0.7058,
+      "step": 303
+    },
+    {
+      "epoch": 2.407920792079208,
+      "grad_norm": 0.4186975177176807,
+      "learning_rate": 2.2479602388887013e-06,
+      "loss": 0.7308,
+      "step": 304
+    },
+    {
+      "epoch": 2.4158415841584158,
+      "grad_norm": 0.41697995471077964,
+      "learning_rate": 2.1899220303518465e-06,
+      "loss": 0.7428,
+      "step": 305
+    },
+    {
+      "epoch": 2.4237623762376237,
+      "grad_norm": 0.4024605920230618,
+      "learning_rate": 2.132550619665168e-06,
+      "loss": 0.6937,
+      "step": 306
+    },
+    {
+      "epoch": 2.4316831683168316,
+      "grad_norm": 0.415257008654532,
+      "learning_rate": 2.075850905004262e-06,
+      "loss": 0.7351,
+      "step": 307
+    },
+    {
+      "epoch": 2.4396039603960396,
+      "grad_norm": 0.40407977073992135,
+      "learning_rate": 2.019827727197605e-06,
+      "loss": 0.7028,
+      "step": 308
+    },
+    {
+      "epoch": 2.4475247524752475,
+      "grad_norm": 0.3935541096805544,
+      "learning_rate": 1.9644858693132627e-06,
+      "loss": 0.7073,
+      "step": 309
+    },
+    {
+      "epoch": 2.4554455445544554,
+      "grad_norm": 0.40998948849676764,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.7084,
+      "step": 310
+    },
+    {
+      "epoch": 2.4633663366336633,
+      "grad_norm": 0.4064763838316956,
+      "learning_rate": 1.855864954336517e-06,
+      "loss": 0.7541,
+      "step": 311
+    },
+    {
+      "epoch": 2.4712871287128713,
+      "grad_norm": 0.40702963715268836,
+      "learning_rate": 1.80259517092779e-06,
+      "loss": 0.7118,
+      "step": 312
+    },
+    {
+      "epoch": 2.479207920792079,
+      "grad_norm": 0.40962380739362325,
+      "learning_rate": 1.7500252540169782e-06,
+      "loss": 0.7149,
+      "step": 313
+    },
+    {
+      "epoch": 2.487128712871287,
+      "grad_norm": 0.4225405507530112,
+      "learning_rate": 1.6981596918444953e-06,
+      "loss": 0.7097,
+      "step": 314
+    },
+    {
+      "epoch": 2.495049504950495,
+      "grad_norm": 0.3974259872963068,
+      "learning_rate": 1.6470029125153463e-06,
+      "loss": 0.7468,
+      "step": 315
+    },
+    {
+      "epoch": 2.502970297029703,
+      "grad_norm": 0.4075694075831413,
+      "learning_rate": 1.596559283621074e-06,
+      "loss": 0.7223,
+      "step": 316
+    },
+    {
+      "epoch": 2.510891089108911,
+      "grad_norm": 0.4032028821038701,
+      "learning_rate": 1.5468331118668655e-06,
+      "loss": 0.7233,
+      "step": 317
+    },
+    {
+      "epoch": 2.518811881188119,
+      "grad_norm": 0.3984358554986335,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.7163,
+      "step": 318
+    },
+    {
+      "epoch": 2.5267326732673268,
+      "grad_norm": 0.39826123904027727,
+      "learning_rate": 1.44955005996669e-06,
+      "loss": 0.7174,
+      "step": 319
+    },
+    {
+      "epoch": 2.5346534653465347,
+      "grad_norm": 0.40725326569026266,
+      "learning_rate": 1.4020014855162755e-06,
+      "loss": 0.7112,
+      "step": 320
+    },
+    {
+      "epoch": 2.5425742574257426,
+      "grad_norm": 0.39814818108116296,
+      "learning_rate": 1.3551869788879213e-06,
+      "loss": 0.7301,
+      "step": 321
+    },
+    {
+      "epoch": 2.5504950495049505,
+      "grad_norm": 0.39471994779707076,
+      "learning_rate": 1.3091105369447166e-06,
+      "loss": 0.7092,
+      "step": 322
+    },
+    {
+      "epoch": 2.5584158415841585,
+      "grad_norm": 0.4165929129276557,
+      "learning_rate": 1.2637760935363053e-06,
+      "loss": 0.7131,
+      "step": 323
+    },
+    {
+      "epoch": 2.5663366336633664,
+      "grad_norm": 0.40067988266060006,
+      "learning_rate": 1.2191875191630209e-06,
+      "loss": 0.7242,
+      "step": 324
+    },
+    {
+      "epoch": 2.5742574257425743,
+      "grad_norm": 0.4150381954280917,
+      "learning_rate": 1.1753486206454433e-06,
+      "loss": 0.7402,
+      "step": 325
+    },
+    {
+      "epoch": 2.5821782178217823,
+      "grad_norm": 0.3920384804019307,
+      "learning_rate": 1.132263140799381e-06,
+      "loss": 0.7105,
+      "step": 326
+    },
+    {
+      "epoch": 2.59009900990099,
+      "grad_norm": 0.3987176952287612,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 0.7144,
+      "step": 327
+    },
+    {
+      "epoch": 2.598019801980198,
+      "grad_norm": 0.41078279785040733,
+      "learning_rate": 1.0483670864493777e-06,
+      "loss": 0.7249,
+      "step": 328
+    },
+    {
+      "epoch": 2.605940594059406,
+      "grad_norm": 0.4040238292412966,
+      "learning_rate": 1.0075636747047446e-06,
+      "loss": 0.7272,
+      "step": 329
+    },
+    {
+      "epoch": 2.613861386138614,
+      "grad_norm": 0.43047282777392387,
+      "learning_rate": 9.675280065387117e-07,
+      "loss": 0.7433,
+      "step": 330
+    },
+    {
+      "epoch": 2.621782178217822,
+      "grad_norm": 0.3922293398745348,
+      "learning_rate": 9.282635000602346e-07,
+      "loss": 0.7071,
+      "step": 331
+    },
+    {
+      "epoch": 2.62970297029703,
+      "grad_norm": 0.41685890998877895,
+      "learning_rate": 8.897735075391156e-07,
+      "loss": 0.7435,
+      "step": 332
+    },
+    {
+      "epoch": 2.6376237623762377,
+      "grad_norm": 0.4060427125681242,
+      "learning_rate": 8.520613151197899e-07,
+      "loss": 0.7065,
+      "step": 333
+    },
+    {
+      "epoch": 2.6455445544554457,
+      "grad_norm": 0.3975045499192803,
+      "learning_rate": 8.151301425407699e-07,
+      "loss": 0.7324,
+      "step": 334
+    },
+    {
+      "epoch": 2.6534653465346536,
+      "grad_norm": 0.39196801398755104,
+      "learning_rate": 7.78983142859755e-07,
+      "loss": 0.714,
+      "step": 335
+    },
+    {
+      "epoch": 2.6613861386138615,
+      "grad_norm": 0.3956193577383561,
+      "learning_rate": 7.43623402184438e-07,
+      "loss": 0.7276,
+      "step": 336
+    },
+    {
+      "epoch": 2.6693069306930695,
+      "grad_norm": 0.3990830893440769,
+      "learning_rate": 7.090539394090135e-07,
+      "loss": 0.7247,
+      "step": 337
+    },
+    {
+      "epoch": 2.6772277227722774,
+      "grad_norm": 0.3930307996524001,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.6925,
+      "step": 338
+    },
+    {
+      "epoch": 2.6851485148514853,
+      "grad_norm": 0.41056613538755815,
+      "learning_rate": 6.422975855264757e-07,
+      "loss": 0.7119,
+      "step": 339
+    },
+    {
+      "epoch": 2.693069306930693,
+      "grad_norm": 0.5308864436453282,
+      "learning_rate": 6.101163938494359e-07,
+      "loss": 0.6739,
+      "step": 340
+    },
+    {
+      "epoch": 2.7009900990099007,
+      "grad_norm": 0.3970396905428287,
+      "learning_rate": 5.78736878445837e-07,
+      "loss": 0.6944,
+      "step": 341
+    },
+    {
+      "epoch": 2.7089108910891087,
+      "grad_norm": 0.40116648564130203,
+      "learning_rate": 5.481617183918053e-07,
+      "loss": 0.6752,
+      "step": 342
+    },
+    {
+      "epoch": 2.7168316831683166,
+      "grad_norm": 0.4288212628472651,
+      "learning_rate": 5.183935240903415e-07,
+      "loss": 0.7268,
+      "step": 343
+    },
+    {
+      "epoch": 2.7247524752475245,
+      "grad_norm": 0.4018223127502873,
+      "learning_rate": 4.894348370484648e-07,
+      "loss": 0.7069,
+      "step": 344
+    },
+    {
+      "epoch": 2.7326732673267324,
+      "grad_norm": 0.45512141312553184,
+      "learning_rate": 4.6128812966021894e-07,
+      "loss": 0.7236,
+      "step": 345
+    },
+    {
+      "epoch": 2.7405940594059404,
+      "grad_norm": 0.40647740230337975,
+      "learning_rate": 4.3395580499559276e-07,
+      "loss": 0.7056,
+      "step": 346
+    },
+    {
+      "epoch": 2.7485148514851483,
+      "grad_norm": 0.7851062640103578,
+      "learning_rate": 4.0744019659535116e-07,
+      "loss": 0.7191,
+      "step": 347
+    },
+    {
+      "epoch": 2.756435643564356,
+      "grad_norm": 0.3918292935567612,
+      "learning_rate": 3.817435682718096e-07,
+      "loss": 0.7331,
+      "step": 348
+    },
+    {
+      "epoch": 2.764356435643564,
+      "grad_norm": 0.40947897586494714,
+      "learning_rate": 3.5686811391555164e-07,
+      "loss": 0.6874,
+      "step": 349
+    },
+    {
+      "epoch": 2.772277227722772,
+      "grad_norm": 0.3980289846234701,
+      "learning_rate": 3.328159573081258e-07,
+      "loss": 0.7299,
+      "step": 350
+    },
+    {
+      "epoch": 2.78019801980198,
+      "grad_norm": 0.3883876533346389,
+      "learning_rate": 3.095891519407246e-07,
+      "loss": 0.705,
+      "step": 351
+    },
+    {
+      "epoch": 2.788118811881188,
+      "grad_norm": 0.4021695381629565,
+      "learning_rate": 2.871896808388608e-07,
+      "loss": 0.7105,
+      "step": 352
+    },
+    {
+      "epoch": 2.796039603960396,
+      "grad_norm": 0.40524014008780573,
+      "learning_rate": 2.656194563930714e-07,
+      "loss": 0.6829,
+      "step": 353
+    },
+    {
+      "epoch": 2.803960396039604,
+      "grad_norm": 0.400098347999415,
+      "learning_rate": 2.44880320195634e-07,
+      "loss": 0.7134,
+      "step": 354
+    },
+    {
+      "epoch": 2.8118811881188117,
+      "grad_norm": 0.39959879213796157,
+      "learning_rate": 2.2497404288334245e-07,
+      "loss": 0.7349,
+      "step": 355
+    },
+    {
+      "epoch": 2.8198019801980196,
+      "grad_norm": 0.404829435915328,
+      "learning_rate": 2.0590232398634114e-07,
+      "loss": 0.7224,
+      "step": 356
+    },
+    {
+      "epoch": 2.8277227722772276,
+      "grad_norm": 0.3988593166231128,
+      "learning_rate": 1.876667917830155e-07,
+      "loss": 0.7137,
+      "step": 357
+    },
+    {
+      "epoch": 2.8356435643564355,
+      "grad_norm": 0.39999015184518205,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.7214,
+      "step": 358
+    },
+    {
+      "epoch": 2.8435643564356434,
+      "grad_norm": 0.40532384840797636,
+      "learning_rate": 1.537104434841641e-07,
+      "loss": 0.7403,
+      "step": 359
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "grad_norm": 0.4072129955656424,
+      "learning_rate": 1.3799252646597428e-07,
+      "loss": 0.7525,
+      "step": 360
+    },
+    {
+      "epoch": 2.8594059405940593,
+      "grad_norm": 0.4081067652201019,
+      "learning_rate": 1.231165940486234e-07,
+      "loss": 0.7119,
+      "step": 361
+    },
+    {
+      "epoch": 2.867326732673267,
+      "grad_norm": 0.40127768445127304,
+      "learning_rate": 1.0908391628854042e-07,
+      "loss": 0.7068,
+      "step": 362
+    },
+    {
+      "epoch": 2.875247524752475,
+      "grad_norm": 0.4056569585309908,
+      "learning_rate": 9.589569124794918e-08,
+      "loss": 0.7327,
+      "step": 363
+    },
+    {
+      "epoch": 2.883168316831683,
+      "grad_norm": 0.39394071807420317,
+      "learning_rate": 8.355304489257254e-08,
+      "loss": 0.7217,
+      "step": 364
+    },
+    {
+      "epoch": 2.891089108910891,
+      "grad_norm": 0.3987850556623756,
+      "learning_rate": 7.205703099551042e-08,
+      "loss": 0.696,
+      "step": 365
+    },
+    {
+      "epoch": 2.899009900990099,
+      "grad_norm": 0.40217224086214826,
+      "learning_rate": 6.140863104726391e-08,
+      "loss": 0.7303,
+      "step": 366
+    },
+    {
+      "epoch": 2.906930693069307,
+      "grad_norm": 0.40009663993330546,
+      "learning_rate": 5.1608754171944555e-08,
+      "loss": 0.7105,
+      "step": 367
+    },
+    {
+      "epoch": 2.9148514851485148,
+      "grad_norm": 0.3967938165718884,
+      "learning_rate": 4.2658237049655325e-08,
+      "loss": 0.7334,
+      "step": 368
+    },
+    {
+      "epoch": 2.9227722772277227,
+      "grad_norm": 0.4086603962701755,
+      "learning_rate": 3.455784384505445e-08,
+      "loss": 0.6938,
+      "step": 369
+    },
+    {
+      "epoch": 2.9306930693069306,
+      "grad_norm": 0.3899469279832273,
+      "learning_rate": 2.7308266142119788e-08,
+      "loss": 0.7172,
+      "step": 370
+    },
+    {
+      "epoch": 2.9386138613861386,
+      "grad_norm": 0.4126769814687196,
+      "learning_rate": 2.0910122885097194e-08,
+      "loss": 0.7112,
+      "step": 371
+    },
+    {
+      "epoch": 2.9465346534653465,
+      "grad_norm": 1.0101608008566858,
+      "learning_rate": 1.5363960325660565e-08,
+      "loss": 0.7177,
+      "step": 372
+    },
+    {
+      "epoch": 2.9544554455445544,
+      "grad_norm": 0.422375267138987,
+      "learning_rate": 1.0670251976275803e-08,
+      "loss": 0.7275,
+      "step": 373
+    },
+    {
+      "epoch": 2.9623762376237623,
+      "grad_norm": 0.3978598838942699,
+      "learning_rate": 6.82939856977094e-09,
+      "loss": 0.7221,
+      "step": 374
+    },
+    {
+      "epoch": 2.9702970297029703,
+      "grad_norm": 0.4100316902452377,
+      "learning_rate": 3.8417280251257235e-09,
+      "loss": 0.7309,
+      "step": 375
+    },
+    {
+      "epoch": 2.978217821782178,
+      "grad_norm": 0.39841317020419215,
+      "learning_rate": 1.7074954194729044e-09,
+      "loss": 0.7361,
+      "step": 376
+    },
+    {
+      "epoch": 2.986138613861386,
+      "grad_norm": 0.39205883398967273,
+      "learning_rate": 4.2688296632120705e-10,
+      "loss": 0.7139,
+      "step": 377
+    },
+    {
+      "epoch": 2.994059405940594,
+      "grad_norm": 0.3914037221232023,
+      "learning_rate": 0.0,
+      "loss": 0.714,
+      "step": 378
+    },
+    {
+      "epoch": 2.994059405940594,
+      "eval_loss": 1.0379831790924072,
+      "eval_runtime": 89.0288,
+      "eval_samples_per_second": 2.988,
+      "eval_steps_per_second": 0.191,
+      "step": 378
+    },
+    {
+      "epoch": 2.994059405940594,
+      "step": 378,
+      "total_flos": 158238674780160.0,
+      "train_loss": 0.8970171990533354,
+      "train_runtime": 67109.8008,
+      "train_samples_per_second": 0.722,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 378,
+  "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": 158238674780160.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}