Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: mistral-community/Mistral-7B-v0.2
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-sft-full
+  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. -->
+
+# zephyr-7b-sft-full
+
+This model is a fine-tuned version of [mistral-community/Mistral-7B-v0.2](https://huggingface.co/mistral-community/Mistral-7B-v0.2) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9390
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.923         | 1.0   | 1090 | 0.9390          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 456447649382400.0,
+    "train_loss": 0.9810463331161289,
+    "train_runtime": 13406.7569,
+    "train_samples": 207864,
+    "train_samples_per_second": 10.4,
+    "train_steps_per_second": 0.081
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bdf598f884cd942b40114e28b0282728f4a21f1fe7f15a5e69fc364713a057
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7718abba8af7a91f22a403088805f752dcb12257304d73d283db9b676c7da18e
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40651c85c99b04fff2857f596b652221f625f15c6ee52121dea8ebdbb7d8908b
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

runs/May17_05-44-34_action-graph-trainer/events.out.tfevents.1715926265.action-graph-trainer.2727348.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc98e399fcfa82a8c8aaba9c675ff49273391c68341fafeeac4f0b5d75ca8e04
-size 47098
+oid sha256:386488904e035de4c05ed84dd293fb023cdeb29069ef7d1062c4e8b3e0c06a52
+size 51521

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 456447649382400.0,
+    "train_loss": 0.9810463331161289,
+    "train_runtime": 13406.7569,
+    "train_samples": 207864,
+    "train_samples_per_second": 10.4,
+    "train_steps_per_second": 0.081
+}

trainer_state.json

@@ -0,0 +1,1571 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1090,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009174311926605505,
+      "grad_norm": 9.797866581519601,
+      "learning_rate": 1.8348623853211012e-07,
+      "loss": 1.146,
+      "step": 1
+    },
+    {
+      "epoch": 0.0045871559633027525,
+      "grad_norm": 8.427718555496059,
+      "learning_rate": 9.174311926605506e-07,
+      "loss": 1.1407,
+      "step": 5
+    },
+    {
+      "epoch": 0.009174311926605505,
+      "grad_norm": 4.092928127427638,
+      "learning_rate": 1.8348623853211011e-06,
+      "loss": 1.052,
+      "step": 10
+    },
+    {
+      "epoch": 0.013761467889908258,
+      "grad_norm": 2.5288720687942816,
+      "learning_rate": 2.7522935779816517e-06,
+      "loss": 1.0303,
+      "step": 15
+    },
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 2.2519839990179045,
+      "learning_rate": 3.6697247706422022e-06,
+      "loss": 0.9989,
+      "step": 20
+    },
+    {
+      "epoch": 0.022935779816513763,
+      "grad_norm": 2.1835658473984263,
+      "learning_rate": 4.587155963302753e-06,
+      "loss": 0.998,
+      "step": 25
+    },
+    {
+      "epoch": 0.027522935779816515,
+      "grad_norm": 2.287263603922945,
+      "learning_rate": 5.504587155963303e-06,
+      "loss": 0.9951,
+      "step": 30
+    },
+    {
+      "epoch": 0.03211009174311927,
+      "grad_norm": 2.434127924697329,
+      "learning_rate": 6.422018348623854e-06,
+      "loss": 0.9918,
+      "step": 35
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 1.8567417457183697,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.9979,
+      "step": 40
+    },
+    {
+      "epoch": 0.04128440366972477,
+      "grad_norm": 2.4003193073390423,
+      "learning_rate": 8.256880733944956e-06,
+      "loss": 0.9819,
+      "step": 45
+    },
+    {
+      "epoch": 0.045871559633027525,
+      "grad_norm": 2.0201383685594076,
+      "learning_rate": 9.174311926605506e-06,
+      "loss": 0.9879,
+      "step": 50
+    },
+    {
+      "epoch": 0.05045871559633028,
+      "grad_norm": 2.211858577649561,
+      "learning_rate": 1.0091743119266055e-05,
+      "loss": 0.9976,
+      "step": 55
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 1.943856442458377,
+      "learning_rate": 1.1009174311926607e-05,
+      "loss": 1.0015,
+      "step": 60
+    },
+    {
+      "epoch": 0.05963302752293578,
+      "grad_norm": 2.158310323614526,
+      "learning_rate": 1.1926605504587156e-05,
+      "loss": 0.9854,
+      "step": 65
+    },
+    {
+      "epoch": 0.06422018348623854,
+      "grad_norm": 2.808086678430107,
+      "learning_rate": 1.2844036697247708e-05,
+      "loss": 0.99,
+      "step": 70
+    },
+    {
+      "epoch": 0.06880733944954129,
+      "grad_norm": 2.9717767512687336,
+      "learning_rate": 1.3761467889908258e-05,
+      "loss": 1.0043,
+      "step": 75
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 2.394726897034978,
+      "learning_rate": 1.4678899082568809e-05,
+      "loss": 0.9934,
+      "step": 80
+    },
+    {
+      "epoch": 0.0779816513761468,
+      "grad_norm": 2.7045539878487044,
+      "learning_rate": 1.559633027522936e-05,
+      "loss": 0.9956,
+      "step": 85
+    },
+    {
+      "epoch": 0.08256880733944955,
+      "grad_norm": 2.770778069055874,
+      "learning_rate": 1.6513761467889912e-05,
+      "loss": 1.0155,
+      "step": 90
+    },
+    {
+      "epoch": 0.0871559633027523,
+      "grad_norm": 2.3762283504209054,
+      "learning_rate": 1.743119266055046e-05,
+      "loss": 1.0242,
+      "step": 95
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 2.509031406395702,
+      "learning_rate": 1.834862385321101e-05,
+      "loss": 1.0002,
+      "step": 100
+    },
+    {
+      "epoch": 0.0963302752293578,
+      "grad_norm": 2.1997287382869333,
+      "learning_rate": 1.9266055045871563e-05,
+      "loss": 1.0169,
+      "step": 105
+    },
+    {
+      "epoch": 0.10091743119266056,
+      "grad_norm": 2.1841582267708333,
+      "learning_rate": 1.999994872196626e-05,
+      "loss": 1.026,
+      "step": 110
+    },
+    {
+      "epoch": 0.10550458715596331,
+      "grad_norm": 2.936698161408905,
+      "learning_rate": 1.9998154046002822e-05,
+      "loss": 1.0091,
+      "step": 115
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 2.3526922344177423,
+      "learning_rate": 1.999379599421534e-05,
+      "loss": 1.0111,
+      "step": 120
+    },
+    {
+      "epoch": 0.11467889908256881,
+      "grad_norm": 2.0102554543255153,
+      "learning_rate": 1.9986875683942535e-05,
+      "loss": 1.0191,
+      "step": 125
+    },
+    {
+      "epoch": 0.11926605504587157,
+      "grad_norm": 1.8656284139873642,
+      "learning_rate": 1.9977394889447526e-05,
+      "loss": 1.0158,
+      "step": 130
+    },
+    {
+      "epoch": 0.12385321100917432,
+      "grad_norm": 1.9067666799593996,
+      "learning_rate": 1.9965356041462954e-05,
+      "loss": 0.996,
+      "step": 135
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 2.09289543401076,
+      "learning_rate": 1.9950762226567783e-05,
+      "loss": 1.0223,
+      "step": 140
+    },
+    {
+      "epoch": 0.13302752293577982,
+      "grad_norm": 2.163029935167911,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 1.0284,
+      "step": 145
+    },
+    {
+      "epoch": 0.13761467889908258,
+      "grad_norm": 2.1355703584941006,
+      "learning_rate": 1.9913925316676946e-05,
+      "loss": 1.0222,
+      "step": 150
+    },
+    {
+      "epoch": 0.14220183486238533,
+      "grad_norm": 1.9312734976395127,
+      "learning_rate": 1.9891691666109112e-05,
+      "loss": 1.045,
+      "step": 155
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 2.0041309459260814,
+      "learning_rate": 1.9866921935064907e-05,
+      "loss": 1.0342,
+      "step": 160
+    },
+    {
+      "epoch": 0.15137614678899083,
+      "grad_norm": 2.062699433171624,
+      "learning_rate": 1.9839622474129595e-05,
+      "loss": 1.0446,
+      "step": 165
+    },
+    {
+      "epoch": 0.1559633027522936,
+      "grad_norm": 1.794061296945893,
+      "learning_rate": 1.9809800282473014e-05,
+      "loss": 1.0325,
+      "step": 170
+    },
+    {
+      "epoch": 0.16055045871559634,
+      "grad_norm": 1.7069314198979184,
+      "learning_rate": 1.977746300605507e-05,
+      "loss": 1.0405,
+      "step": 175
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 1.8941763788054986,
+      "learning_rate": 1.9742618935665478e-05,
+      "loss": 1.0314,
+      "step": 180
+    },
+    {
+      "epoch": 0.16972477064220184,
+      "grad_norm": 1.890460224553765,
+      "learning_rate": 1.9705277004798072e-05,
+      "loss": 1.0371,
+      "step": 185
+    },
+    {
+      "epoch": 0.1743119266055046,
+      "grad_norm": 1.7702822374171037,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 1.0422,
+      "step": 190
+    },
+    {
+      "epoch": 0.17889908256880735,
+      "grad_norm": 2.292037944956991,
+      "learning_rate": 1.9623138495219292e-05,
+      "loss": 1.0258,
+      "step": 195
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 1.9163146553783408,
+      "learning_rate": 1.957836297558229e-05,
+      "loss": 1.0284,
+      "step": 200
+    },
+    {
+      "epoch": 0.18807339449541285,
+      "grad_norm": 1.8935048040607476,
+      "learning_rate": 1.9531131708217005e-05,
+      "loss": 1.0282,
+      "step": 205
+    },
+    {
+      "epoch": 0.1926605504587156,
+      "grad_norm": 1.7860045810763372,
+      "learning_rate": 1.948145680250766e-05,
+      "loss": 1.0227,
+      "step": 210
+    },
+    {
+      "epoch": 0.19724770642201836,
+      "grad_norm": 1.8083970356723782,
+      "learning_rate": 1.9429350994350483e-05,
+      "loss": 1.0347,
+      "step": 215
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 1.6934436772369132,
+      "learning_rate": 1.93748276428884e-05,
+      "loss": 1.0422,
+      "step": 220
+    },
+    {
+      "epoch": 0.20642201834862386,
+      "grad_norm": 1.8100390462895424,
+      "learning_rate": 1.931790072708596e-05,
+      "loss": 1.0269,
+      "step": 225
+    },
+    {
+      "epoch": 0.21100917431192662,
+      "grad_norm": 1.8394285930837164,
+      "learning_rate": 1.9258584842145342e-05,
+      "loss": 1.0472,
+      "step": 230
+    },
+    {
+      "epoch": 0.21559633027522937,
+      "grad_norm": 2.0864796192720774,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 1.028,
+      "step": 235
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 1.9906142761148835,
+      "learning_rate": 1.913284760423745e-05,
+      "loss": 1.0321,
+      "step": 240
+    },
+    {
+      "epoch": 0.22477064220183487,
+      "grad_norm": 1.8346043792060736,
+      "learning_rate": 1.9066458488400586e-05,
+      "loss": 1.031,
+      "step": 245
+    },
+    {
+      "epoch": 0.22935779816513763,
+      "grad_norm": 1.75807456533747,
+      "learning_rate": 1.8997744869421248e-05,
+      "loss": 1.0258,
+      "step": 250
+    },
+    {
+      "epoch": 0.23394495412844038,
+      "grad_norm": 1.7950761001144098,
+      "learning_rate": 1.8926724364434447e-05,
+      "loss": 1.0182,
+      "step": 255
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 1.821365158517499,
+      "learning_rate": 1.8853415182025953e-05,
+      "loss": 1.032,
+      "step": 260
+    },
+    {
+      "epoch": 0.24311926605504589,
+      "grad_norm": 1.7138176018422528,
+      "learning_rate": 1.8777836117563894e-05,
+      "loss": 1.0285,
+      "step": 265
+    },
+    {
+      "epoch": 0.24770642201834864,
+      "grad_norm": 1.6119249956139892,
+      "learning_rate": 1.8700006548379898e-05,
+      "loss": 1.0226,
+      "step": 270
+    },
+    {
+      "epoch": 0.25229357798165136,
+      "grad_norm": 1.6075787071095569,
+      "learning_rate": 1.861994642880105e-05,
+      "loss": 1.0441,
+      "step": 275
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 1.6370412009626971,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 1.0325,
+      "step": 280
+    },
+    {
+      "epoch": 0.26146788990825687,
+      "grad_norm": 1.7230515975187888,
+      "learning_rate": 1.845321720990181e-05,
+      "loss": 1.0348,
+      "step": 285
+    },
+    {
+      "epoch": 0.26605504587155965,
+      "grad_norm": 1.6235398322699879,
+      "learning_rate": 1.8366590857437182e-05,
+      "loss": 1.0373,
+      "step": 290
+    },
+    {
+      "epoch": 0.2706422018348624,
+      "grad_norm": 1.8167408195301202,
+      "learning_rate": 1.8277819437329577e-05,
+      "loss": 1.0235,
+      "step": 295
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 1.701844754548217,
+      "learning_rate": 1.8186925709231534e-05,
+      "loss": 1.0366,
+      "step": 300
+    },
+    {
+      "epoch": 0.2798165137614679,
+      "grad_norm": 1.5919168264308288,
+      "learning_rate": 1.809393297692334e-05,
+      "loss": 1.0292,
+      "step": 305
+    },
+    {
+      "epoch": 0.28440366972477066,
+      "grad_norm": 1.7948244166489418,
+      "learning_rate": 1.799886508233829e-05,
+      "loss": 1.0458,
+      "step": 310
+    },
+    {
+      "epoch": 0.2889908256880734,
+      "grad_norm": 1.6845863944203259,
+      "learning_rate": 1.790174639944997e-05,
+      "loss": 1.0422,
+      "step": 315
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 1.6627384237203684,
+      "learning_rate": 1.780260182802314e-05,
+      "loss": 1.0309,
+      "step": 320
+    },
+    {
+      "epoch": 0.2981651376146789,
+      "grad_norm": 1.78048904429509,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 1.0362,
+      "step": 325
+    },
+    {
+      "epoch": 0.30275229357798167,
+      "grad_norm": 1.621206798299626,
+      "learning_rate": 1.7598337209132142e-05,
+      "loss": 1.0189,
+      "step": 330
+    },
+    {
+      "epoch": 0.3073394495412844,
+      "grad_norm": 1.5421888344834969,
+      "learning_rate": 1.7493269532033882e-05,
+      "loss": 1.0199,
+      "step": 335
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 1.528075273938717,
+      "learning_rate": 1.738628069370195e-05,
+      "loss": 1.0312,
+      "step": 340
+    },
+    {
+      "epoch": 0.3165137614678899,
+      "grad_norm": 1.610547863200134,
+      "learning_rate": 1.7277398124460022e-05,
+      "loss": 1.0265,
+      "step": 345
+    },
+    {
+      "epoch": 0.3211009174311927,
+      "grad_norm": 1.547322038003979,
+      "learning_rate": 1.71666497401558e-05,
+      "loss": 0.9964,
+      "step": 350
+    },
+    {
+      "epoch": 0.3256880733944954,
+      "grad_norm": 1.622700336087546,
+      "learning_rate": 1.7054063935003813e-05,
+      "loss": 1.0288,
+      "step": 355
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 1.7814950838467476,
+      "learning_rate": 1.6939669574305565e-05,
+      "loss": 1.0123,
+      "step": 360
+    },
+    {
+      "epoch": 0.3348623853211009,
+      "grad_norm": 1.522218935182621,
+      "learning_rate": 1.6823495987048922e-05,
+      "loss": 1.0139,
+      "step": 365
+    },
+    {
+      "epoch": 0.3394495412844037,
+      "grad_norm": 1.6729699264181774,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 1.0168,
+      "step": 370
+    },
+    {
+      "epoch": 0.3440366972477064,
+      "grad_norm": 1.6039605046472551,
+      "learning_rate": 1.6585930722009602e-05,
+      "loss": 1.0385,
+      "step": 375
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 1.4788794149889521,
+      "learning_rate": 1.6464599952375998e-05,
+      "loss": 1.0258,
+      "step": 380
+    },
+    {
+      "epoch": 0.3532110091743119,
+      "grad_norm": 1.504660109687917,
+      "learning_rate": 1.63416117568662e-05,
+      "loss": 1.0199,
+      "step": 385
+    },
+    {
+      "epoch": 0.3577981651376147,
+      "grad_norm": 1.5030704545753268,
+      "learning_rate": 1.621699766779763e-05,
+      "loss": 1.0164,
+      "step": 390
+    },
+    {
+      "epoch": 0.3623853211009174,
+      "grad_norm": 1.4694185354290437,
+      "learning_rate": 1.6090789634342278e-05,
+      "loss": 1.008,
+      "step": 395
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 1.502605819170643,
+      "learning_rate": 1.5963020014335437e-05,
+      "loss": 1.014,
+      "step": 400
+    },
+    {
+      "epoch": 0.37155963302752293,
+      "grad_norm": 1.5065560011505659,
+      "learning_rate": 1.583372156597961e-05,
+      "loss": 1.0068,
+      "step": 405
+    },
+    {
+      "epoch": 0.3761467889908257,
+      "grad_norm": 1.4320112984208702,
+      "learning_rate": 1.570292743944583e-05,
+      "loss": 1.0058,
+      "step": 410
+    },
+    {
+      "epoch": 0.38073394495412843,
+      "grad_norm": 1.4326401831034563,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 1.025,
+      "step": 415
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 1.488582529852783,
+      "learning_rate": 1.5436986661277578e-05,
+      "loss": 1.0171,
+      "step": 420
+    },
+    {
+      "epoch": 0.38990825688073394,
+      "grad_norm": 1.5853664334620217,
+      "learning_rate": 1.530190819284555e-05,
+      "loss": 1.0062,
+      "step": 425
+    },
+    {
+      "epoch": 0.3944954128440367,
+      "grad_norm": 1.6376346358210006,
+      "learning_rate": 1.5165470395159314e-05,
+      "loss": 1.0362,
+      "step": 430
+    },
+    {
+      "epoch": 0.39908256880733944,
+      "grad_norm": 2.107700540823469,
+      "learning_rate": 1.5027708248811331e-05,
+      "loss": 1.0036,
+      "step": 435
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 1.482808306893593,
+      "learning_rate": 1.4888657073937077e-05,
+      "loss": 1.0125,
+      "step": 440
+    },
+    {
+      "epoch": 0.40825688073394495,
+      "grad_norm": 1.5321553428199717,
+      "learning_rate": 1.4748352521159492e-05,
+      "loss": 0.9996,
+      "step": 445
+    },
+    {
+      "epoch": 0.41284403669724773,
+      "grad_norm": 1.4182290148630876,
+      "learning_rate": 1.4606830562448692e-05,
+      "loss": 1.0078,
+      "step": 450
+    },
+    {
+      "epoch": 0.41743119266055045,
+      "grad_norm": 1.652462912329951,
+      "learning_rate": 1.4464127481899312e-05,
+      "loss": 1.0095,
+      "step": 455
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 1.4134871643935982,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 1.0086,
+      "step": 460
+    },
+    {
+      "epoch": 0.42660550458715596,
+      "grad_norm": 1.4681250077131003,
+      "learning_rate": 1.4175324596392075e-05,
+      "loss": 1.0228,
+      "step": 465
+    },
+    {
+      "epoch": 0.43119266055045874,
+      "grad_norm": 1.5879317091831868,
+      "learning_rate": 1.402929883613599e-05,
+      "loss": 1.009,
+      "step": 470
+    },
+    {
+      "epoch": 0.43577981651376146,
+      "grad_norm": 1.482581286022142,
+      "learning_rate": 1.3882240024460928e-05,
+      "loss": 0.9949,
+      "step": 475
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 1.5572687872922886,
+      "learning_rate": 1.3734185865027061e-05,
+      "loss": 1.0132,
+      "step": 480
+    },
+    {
+      "epoch": 0.44495412844036697,
+      "grad_norm": 1.4871057091418516,
+      "learning_rate": 1.358517431668672e-05,
+      "loss": 1.002,
+      "step": 485
+    },
+    {
+      "epoch": 0.44954128440366975,
+      "grad_norm": 1.3354034524950988,
+      "learning_rate": 1.3435243583752294e-05,
+      "loss": 0.9966,
+      "step": 490
+    },
+    {
+      "epoch": 0.4541284403669725,
+      "grad_norm": 1.411120877551773,
+      "learning_rate": 1.3284432106201233e-05,
+      "loss": 0.9905,
+      "step": 495
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 1.5259817407747036,
+      "learning_rate": 1.313277854982062e-05,
+      "loss": 1.0106,
+      "step": 500
+    },
+    {
+      "epoch": 0.463302752293578,
+      "grad_norm": 1.5742889406672467,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 0.9891,
+      "step": 505
+    },
+    {
+      "epoch": 0.46788990825688076,
+      "grad_norm": 1.4784810162072364,
+      "learning_rate": 1.2827100933231904e-05,
+      "loss": 1.0079,
+      "step": 510
+    },
+    {
+      "epoch": 0.4724770642201835,
+      "grad_norm": 1.6554360721057533,
+      "learning_rate": 1.2673155244151985e-05,
+      "loss": 1.0075,
+      "step": 515
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 1.53715721377512,
+      "learning_rate": 1.2518524198405699e-05,
+      "loss": 1.0017,
+      "step": 520
+    },
+    {
+      "epoch": 0.481651376146789,
+      "grad_norm": 1.5071083010755015,
+      "learning_rate": 1.2363247441059775e-05,
+      "loss": 0.9877,
+      "step": 525
+    },
+    {
+      "epoch": 0.48623853211009177,
+      "grad_norm": 1.4445010695511022,
+      "learning_rate": 1.2207364782731657e-05,
+      "loss": 1.0119,
+      "step": 530
+    },
+    {
+      "epoch": 0.4908256880733945,
+      "grad_norm": 1.3964846678923748,
+      "learning_rate": 1.2050916189382646e-05,
+      "loss": 0.9755,
+      "step": 535
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 1.5013913915153163,
+      "learning_rate": 1.189394177207125e-05,
+      "loss": 0.9836,
+      "step": 540
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.3940120479721783,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.9906,
+      "step": 545
+    },
+    {
+      "epoch": 0.5045871559633027,
+      "grad_norm": 1.4590101843259737,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 0.9667,
+      "step": 550
+    },
+    {
+      "epoch": 0.5091743119266054,
+      "grad_norm": 1.4275421198403777,
+      "learning_rate": 1.1420266647205232e-05,
+      "loss": 0.9775,
+      "step": 555
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 1.4318930366924776,
+      "learning_rate": 1.1261592585930576e-05,
+      "loss": 0.987,
+      "step": 560
+    },
+    {
+      "epoch": 0.518348623853211,
+      "grad_norm": 1.4029387505115745,
+      "learning_rate": 1.1102595071354471e-05,
+      "loss": 0.9877,
+      "step": 565
+    },
+    {
+      "epoch": 0.5229357798165137,
+      "grad_norm": 1.40361379595912,
+      "learning_rate": 1.0943314868040365e-05,
+      "loss": 0.9809,
+      "step": 570
+    },
+    {
+      "epoch": 0.5275229357798165,
+      "grad_norm": 1.620813299969718,
+      "learning_rate": 1.0783792813028828e-05,
+      "loss": 0.9916,
+      "step": 575
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 1.4267199847240755,
+      "learning_rate": 1.0624069805367558e-05,
+      "loss": 0.9724,
+      "step": 580
+    },
+    {
+      "epoch": 0.536697247706422,
+      "grad_norm": 1.3967830543656679,
+      "learning_rate": 1.0464186795625481e-05,
+      "loss": 0.9754,
+      "step": 585
+    },
+    {
+      "epoch": 0.5412844036697247,
+      "grad_norm": 1.4999292927669836,
+      "learning_rate": 1.0304184775393642e-05,
+      "loss": 0.986,
+      "step": 590
+    },
+    {
+      "epoch": 0.5458715596330275,
+      "grad_norm": 1.4423550886024152,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 0.9714,
+      "step": 595
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 1.3531728935425589,
+      "learning_rate": 9.983987811869863e-06,
+      "loss": 0.964,
+      "step": 600
+    },
+    {
+      "epoch": 0.555045871559633,
+      "grad_norm": 1.3951653536410364,
+      "learning_rate": 9.823874962247565e-06,
+      "loss": 0.9889,
+      "step": 605
+    },
+    {
+      "epoch": 0.5596330275229358,
+      "grad_norm": 1.4511174833378555,
+      "learning_rate": 9.663807268427197e-06,
+      "loss": 0.9523,
+      "step": 610
+    },
+    {
+      "epoch": 0.5642201834862385,
+      "grad_norm": 1.3735460270489455,
+      "learning_rate": 9.503825769350016e-06,
+      "loss": 0.9784,
+      "step": 615
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 1.4407979891800395,
+      "learning_rate": 9.343971481858246e-06,
+      "loss": 0.9751,
+      "step": 620
+    },
+    {
+      "epoch": 0.573394495412844,
+      "grad_norm": 1.3764958465136419,
+      "learning_rate": 9.184285390178978e-06,
+      "loss": 0.971,
+      "step": 625
+    },
+    {
+      "epoch": 0.5779816513761468,
+      "grad_norm": 1.3475749847045115,
+      "learning_rate": 9.024808435416435e-06,
+      "loss": 0.9588,
+      "step": 630
+    },
+    {
+      "epoch": 0.5825688073394495,
+      "grad_norm": 1.4165511547354543,
+      "learning_rate": 8.865581505055292e-06,
+      "loss": 0.9678,
+      "step": 635
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 1.409796656867394,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 0.9635,
+      "step": 640
+    },
+    {
+      "epoch": 0.591743119266055,
+      "grad_norm": 1.4960028493594866,
+      "learning_rate": 8.548040936496989e-06,
+      "loss": 0.9686,
+      "step": 645
+    },
+    {
+      "epoch": 0.5963302752293578,
+      "grad_norm": 1.4512436818877472,
+      "learning_rate": 8.389808710909881e-06,
+      "loss": 0.9715,
+      "step": 650
+    },
+    {
+      "epoch": 0.6009174311926605,
+      "grad_norm": 1.389169191448506,
+      "learning_rate": 8.231989314071318e-06,
+      "loss": 0.97,
+      "step": 655
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 1.4286996459347407,
+      "learning_rate": 8.07462320849313e-06,
+      "loss": 0.9861,
+      "step": 660
+    },
+    {
+      "epoch": 0.6100917431192661,
+      "grad_norm": 1.389233177009358,
+      "learning_rate": 7.917750740470116e-06,
+      "loss": 0.9633,
+      "step": 665
+    },
+    {
+      "epoch": 0.6146788990825688,
+      "grad_norm": 1.3775631463747944,
+      "learning_rate": 7.761412129735853e-06,
+      "loss": 0.9625,
+      "step": 670
+    },
+    {
+      "epoch": 0.6192660550458715,
+      "grad_norm": 1.4009260092646365,
+      "learning_rate": 7.605647459150961e-06,
+      "loss": 0.9724,
+      "step": 675
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 1.3225550273394528,
+      "learning_rate": 7.4504966644264775e-06,
+      "loss": 0.9526,
+      "step": 680
+    },
+    {
+      "epoch": 0.6284403669724771,
+      "grad_norm": 1.3609358732641874,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 0.9631,
+      "step": 685
+    },
+    {
+      "epoch": 0.6330275229357798,
+      "grad_norm": 1.3744909149495705,
+      "learning_rate": 7.142195648261747e-06,
+      "loss": 0.9736,
+      "step": 690
+    },
+    {
+      "epoch": 0.6376146788990825,
+      "grad_norm": 1.344696610604751,
+      "learning_rate": 6.989124470549746e-06,
+      "loss": 0.9423,
+      "step": 695
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 1.337942065126883,
+      "learning_rate": 6.83682523588902e-06,
+      "loss": 0.9655,
+      "step": 700
+    },
+    {
+      "epoch": 0.6467889908256881,
+      "grad_norm": 1.3614847141575495,
+      "learning_rate": 6.685336991505122e-06,
+      "loss": 0.9678,
+      "step": 705
+    },
+    {
+      "epoch": 0.6513761467889908,
+      "grad_norm": 1.3230900779999575,
+      "learning_rate": 6.5346985766979384e-06,
+      "loss": 0.9571,
+      "step": 710
+    },
+    {
+      "epoch": 0.6559633027522935,
+      "grad_norm": 1.334659859344649,
+      "learning_rate": 6.384948612883872e-06,
+      "loss": 0.9612,
+      "step": 715
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 1.30456120316146,
+      "learning_rate": 6.2361254936939e-06,
+      "loss": 0.9617,
+      "step": 720
+    },
+    {
+      "epoch": 0.6651376146788991,
+      "grad_norm": 1.323565171442615,
+      "learning_rate": 6.0882673751300235e-06,
+      "loss": 0.9507,
+      "step": 725
+    },
+    {
+      "epoch": 0.6697247706422018,
+      "grad_norm": 1.3345956617227264,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 0.9589,
+      "step": 730
+    },
+    {
+      "epoch": 0.6743119266055045,
+      "grad_norm": 1.4304814389946796,
+      "learning_rate": 5.79559751711138e-06,
+      "loss": 0.9505,
+      "step": 735
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 1.3356742272309972,
+      "learning_rate": 5.650860813791786e-06,
+      "loss": 0.9518,
+      "step": 740
+    },
+    {
+      "epoch": 0.6834862385321101,
+      "grad_norm": 1.4025057276173587,
+      "learning_rate": 5.507239164130501e-06,
+      "loss": 0.9513,
+      "step": 745
+    },
+    {
+      "epoch": 0.6880733944954128,
+      "grad_norm": 1.3358485503012785,
+      "learning_rate": 5.364769390551225e-06,
+      "loss": 0.9683,
+      "step": 750
+    },
+    {
+      "epoch": 0.6926605504587156,
+      "grad_norm": 1.3082785185345842,
+      "learning_rate": 5.223488020154028e-06,
+      "loss": 0.9624,
+      "step": 755
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 1.3522908131265046,
+      "learning_rate": 5.083431275350312e-06,
+      "loss": 0.9283,
+      "step": 760
+    },
+    {
+      "epoch": 0.7018348623853211,
+      "grad_norm": 1.2922554744460317,
+      "learning_rate": 4.9446350645759885e-06,
+      "loss": 0.9441,
+      "step": 765
+    },
+    {
+      "epoch": 0.7064220183486238,
+      "grad_norm": 1.4114956038550543,
+      "learning_rate": 4.807134973085036e-06,
+      "loss": 0.9697,
+      "step": 770
+    },
+    {
+      "epoch": 0.7110091743119266,
+      "grad_norm": 1.2696644616371817,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 0.9373,
+      "step": 775
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 1.4629620137851231,
+      "learning_rate": 4.53616381840377e-06,
+      "loss": 0.95,
+      "step": 780
+    },
+    {
+      "epoch": 0.7201834862385321,
+      "grad_norm": 1.3714565256021574,
+      "learning_rate": 4.402762228128531e-06,
+      "loss": 0.9417,
+      "step": 785
+    },
+    {
+      "epoch": 0.7247706422018348,
+      "grad_norm": 1.4183545202083996,
+      "learning_rate": 4.270795685155001e-06,
+      "loss": 0.9499,
+      "step": 790
+    },
+    {
+      "epoch": 0.7293577981651376,
+      "grad_norm": 1.3205369291505886,
+      "learning_rate": 4.140298023713416e-06,
+      "loss": 0.9323,
+      "step": 795
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 1.370701834137729,
+      "learning_rate": 4.0113027014349374e-06,
+      "loss": 0.9168,
+      "step": 800
+    },
+    {
+      "epoch": 0.7385321100917431,
+      "grad_norm": 1.3042672508858097,
+      "learning_rate": 3.883842790773647e-06,
+      "loss": 0.9592,
+      "step": 805
+    },
+    {
+      "epoch": 0.7431192660550459,
+      "grad_norm": 1.3064123913534935,
+      "learning_rate": 3.757950970527249e-06,
+      "loss": 0.9284,
+      "step": 810
+    },
+    {
+      "epoch": 0.7477064220183486,
+      "grad_norm": 1.3065430427090394,
+      "learning_rate": 3.633659517458736e-06,
+      "loss": 0.9273,
+      "step": 815
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 1.2703070702836412,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 0.9253,
+      "step": 820
+    },
+    {
+      "epoch": 0.7568807339449541,
+      "grad_norm": 1.3398945194343388,
+      "learning_rate": 3.39000476018726e-06,
+      "loss": 0.9288,
+      "step": 825
+    },
+    {
+      "epoch": 0.7614678899082569,
+      "grad_norm": 1.2778852672739778,
+      "learning_rate": 3.2707039253872796e-06,
+      "loss": 0.9254,
+      "step": 830
+    },
+    {
+      "epoch": 0.7660550458715596,
+      "grad_norm": 1.3303966067925974,
+      "learning_rate": 3.153128380554941e-06,
+      "loss": 0.9338,
+      "step": 835
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 1.3030003909557433,
+      "learning_rate": 3.037308270285709e-06,
+      "loss": 0.925,
+      "step": 840
+    },
+    {
+      "epoch": 0.7752293577981652,
+      "grad_norm": 1.2744506690007673,
+      "learning_rate": 2.923273289108115e-06,
+      "loss": 0.9428,
+      "step": 845
+    },
+    {
+      "epoch": 0.7798165137614679,
+      "grad_norm": 1.2923362843968602,
+      "learning_rate": 2.8110526738705345e-06,
+      "loss": 0.9262,
+      "step": 850
+    },
+    {
+      "epoch": 0.7844036697247706,
+      "grad_norm": 1.307141046764321,
+      "learning_rate": 2.700675196245288e-06,
+      "loss": 0.9419,
+      "step": 855
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 1.272783570802427,
+      "learning_rate": 2.592169155352031e-06,
+      "loss": 0.9431,
+      "step": 860
+    },
+    {
+      "epoch": 0.7935779816513762,
+      "grad_norm": 1.2769597385673763,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 0.9458,
+      "step": 865
+    },
+    {
+      "epoch": 0.7981651376146789,
+      "grad_norm": 1.348054241772535,
+      "learning_rate": 2.3808821740669608e-06,
+      "loss": 0.9381,
+      "step": 870
+    },
+    {
+      "epoch": 0.8027522935779816,
+      "grad_norm": 1.3328586135999967,
+      "learning_rate": 2.2781554044688015e-06,
+      "loss": 0.9402,
+      "step": 875
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 1.3091185173403772,
+      "learning_rate": 2.1774083993013715e-06,
+      "loss": 0.9376,
+      "step": 880
+    },
+    {
+      "epoch": 0.8119266055045872,
+      "grad_norm": 1.3126841182660047,
+      "learning_rate": 2.0786669885765044e-06,
+      "loss": 0.9286,
+      "step": 885
+    },
+    {
+      "epoch": 0.8165137614678899,
+      "grad_norm": 1.299660265289108,
+      "learning_rate": 1.981956488101898e-06,
+      "loss": 0.9419,
+      "step": 890
+    },
+    {
+      "epoch": 0.8211009174311926,
+      "grad_norm": 1.331079398798441,
+      "learning_rate": 1.8873016929904942e-06,
+      "loss": 0.9444,
+      "step": 895
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 1.2590818401281205,
+      "learning_rate": 1.7947268713034128e-06,
+      "loss": 0.9136,
+      "step": 900
+    },
+    {
+      "epoch": 0.8302752293577982,
+      "grad_norm": 1.26927535411352,
+      "learning_rate": 1.704255757827963e-06,
+      "loss": 0.9175,
+      "step": 905
+    },
+    {
+      "epoch": 0.8348623853211009,
+      "grad_norm": 1.3210015666942456,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 0.9328,
+      "step": 910
+    },
+    {
+      "epoch": 0.8394495412844036,
+      "grad_norm": 1.3123997636377258,
+      "learning_rate": 1.529716891919074e-06,
+      "loss": 0.9416,
+      "step": 915
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 1.2908364394847265,
+      "learning_rate": 1.4456938886170413e-06,
+      "loss": 0.9129,
+      "step": 920
+    },
+    {
+      "epoch": 0.8486238532110092,
+      "grad_norm": 1.3182702591467457,
+      "learning_rate": 1.3638640803164516e-06,
+      "loss": 0.9261,
+      "step": 925
+    },
+    {
+      "epoch": 0.8532110091743119,
+      "grad_norm": 1.4674739471762706,
+      "learning_rate": 1.2842484469453365e-06,
+      "loss": 0.9159,
+      "step": 930
+    },
+    {
+      "epoch": 0.8577981651376146,
+      "grad_norm": 1.3130778393525182,
+      "learning_rate": 1.2068674007506787e-06,
+      "loss": 0.9304,
+      "step": 935
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 1.3697197759877109,
+      "learning_rate": 1.1317407810650372e-06,
+      "loss": 0.9289,
+      "step": 940
+    },
+    {
+      "epoch": 0.8669724770642202,
+      "grad_norm": 1.2668626903844098,
+      "learning_rate": 1.0588878492200261e-06,
+      "loss": 0.9349,
+      "step": 945
+    },
+    {
+      "epoch": 0.8715596330275229,
+      "grad_norm": 1.2955211201170846,
+      "learning_rate": 9.883272836080116e-07,
+      "loss": 0.9221,
+      "step": 950
+    },
+    {
+      "epoch": 0.8761467889908257,
+      "grad_norm": 1.30796302659334,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 0.935,
+      "step": 955
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 1.302371050855527,
+      "learning_rate": 8.541550213737171e-07,
+      "loss": 0.9131,
+      "step": 960
+    },
+    {
+      "epoch": 0.8853211009174312,
+      "grad_norm": 1.2686626009853337,
+      "learning_rate": 7.905777244947954e-07,
+      "loss": 0.9196,
+      "step": 965
+    },
+    {
+      "epoch": 0.8899082568807339,
+      "grad_norm": 1.33952018651438,
+      "learning_rate": 7.293615845160196e-07,
+      "loss": 0.9303,
+      "step": 970
+    },
+    {
+      "epoch": 0.8944954128440367,
+      "grad_norm": 1.3142004093323376,
+      "learning_rate": 6.705222963319191e-07,
+      "loss": 0.9406,
+      "step": 975
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 1.2910709983882336,
+      "learning_rate": 6.140749454480932e-07,
+      "loss": 0.9134,
+      "step": 980
+    },
+    {
+      "epoch": 0.9036697247706422,
+      "grad_norm": 1.3052663290487918,
+      "learning_rate": 5.600340041135133e-07,
+      "loss": 0.9199,
+      "step": 985
+    },
+    {
+      "epoch": 0.908256880733945,
+      "grad_norm": 1.3197825777884429,
+      "learning_rate": 5.0841332761005e-07,
+      "loss": 0.9351,
+      "step": 990
+    },
+    {
+      "epoch": 0.9128440366972477,
+      "grad_norm": 1.2050266272600134,
+      "learning_rate": 4.592261507001994e-07,
+      "loss": 0.9164,
+      "step": 995
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 1.2774181379109981,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 0.9224,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9220183486238532,
+      "grad_norm": 1.2851660562840292,
+      "learning_rate": 3.6820211191520127e-07,
+      "loss": 0.9261,
+      "step": 1005
+    },
+    {
+      "epoch": 0.926605504587156,
+      "grad_norm": 1.3016157142054157,
+      "learning_rate": 3.263885872300343e-07,
+      "loss": 0.9252,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9311926605504587,
+      "grad_norm": 1.2470330025991352,
+      "learning_rate": 2.870552305351382e-07,
+      "loss": 0.903,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 1.2776227693612163,
+      "learning_rate": 2.5021212630962246e-07,
+      "loss": 0.9297,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9403669724770642,
+      "grad_norm": 1.2381197028921025,
+      "learning_rate": 2.158687205694443e-07,
+      "loss": 0.9094,
+      "step": 1025
+    },
+    {
+      "epoch": 0.944954128440367,
+      "grad_norm": 1.2836110047083185,
+      "learning_rate": 1.840338184455881e-07,
+      "loss": 0.9294,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9495412844036697,
+      "grad_norm": 1.2718038074603693,
+      "learning_rate": 1.5471558192656776e-07,
+      "loss": 0.9187,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 1.241258270519395,
+      "learning_rate": 1.279215277658097e-07,
+      "loss": 0.9341,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9587155963302753,
+      "grad_norm": 1.305186814508952,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 0.9275,
+      "step": 1045
+    },
+    {
+      "epoch": 0.963302752293578,
+      "grad_norm": 1.2717320188551713,
+      "learning_rate": 8.19327959602012e-08,
+      "loss": 0.9371,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9678899082568807,
+      "grad_norm": 1.284871662304039,
+      "learning_rate": 6.274990913221035e-08,
+      "loss": 0.9311,
+      "step": 1055
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 1.2652485475313338,
+      "learning_rate": 4.6114783273213395e-08,
+      "loss": 0.9158,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9770642201834863,
+      "grad_norm": 1.2767791748309611,
+      "learning_rate": 3.203168337845508e-08,
+      "loss": 0.9089,
+      "step": 1065
+    },
+    {
+      "epoch": 0.981651376146789,
+      "grad_norm": 1.2768060229936837,
+      "learning_rate": 2.05042201422323e-08,
+      "loss": 0.9185,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9862385321100917,
+      "grad_norm": 1.3226366887213121,
+      "learning_rate": 1.1535349032167908e-08,
+      "loss": 0.9011,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 1.2648568877097428,
+      "learning_rate": 5.127369531473525e-09,
+      "loss": 0.9305,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9954128440366973,
+      "grad_norm": 1.2794584435070722,
+      "learning_rate": 1.2819245493955746e-09,
+      "loss": 0.9269,
+      "step": 1085
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.381828304372254,
+      "learning_rate": 0.0,
+      "loss": 0.923,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9389663338661194,
+      "eval_runtime": 334.0997,
+      "eval_samples_per_second": 46.187,
+      "eval_steps_per_second": 0.724,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "step": 1090,
+      "total_flos": 456447649382400.0,
+      "train_loss": 0.9810463331161289,
+      "train_runtime": 13406.7569,
+      "train_samples_per_second": 10.4,
+      "train_steps_per_second": 0.081
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1090,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 456447649382400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}