Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3933
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.3906        | 1.0   | 1090 | 4.3933          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 4.5692141799751775,
+    "train_runtime": 12438.5839,
+    "train_samples": 207864,
+    "train_samples_per_second": 11.209,
+    "train_steps_per_second": 0.088
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557e5b8962825c82236907a35567a71e440214b05c49fe37910578b0ad7dfacb
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85603f8a58aebeb3d30ccc6245faf4ecfa0565d68d37081afa7925c74c76fe0
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5715522380d513b3b9d99618d5a931d0ca6b9fe954de4141198a4ce6c7edf6e
+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/Mar14_04-20-48_a100-80-8-zifeng-2/events.out.tfevents.1710390956.a100-80-8-zifeng-2.1158576.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b14d00c1516a7eaeb2b9ea1affe02d8af8e7a70713be568db198b737b862a9
-size 46983
+oid sha256:d9a6e608065e060eb6f70619157f342eccafaf80121aa24fb3ed3a2da2f14f9a
+size 51406

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 4.5692141799751775,
+    "train_runtime": 12438.5839,
+    "train_samples": 207864,
+    "train_samples_per_second": 11.209,
+    "train_steps_per_second": 0.088
+}

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": 0.0,
+      "grad_norm": 9.363638838369855,
+      "learning_rate": 1.8348623853211012e-07,
+      "loss": 1.1557,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 7.698313407130926,
+      "learning_rate": 9.174311926605506e-07,
+      "loss": 1.1258,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.550657581482179,
+      "learning_rate": 1.8348623853211011e-06,
+      "loss": 1.0811,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.1206535230799584,
+      "learning_rate": 2.7522935779816517e-06,
+      "loss": 1.0172,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.6667669157454204,
+      "learning_rate": 3.6697247706422022e-06,
+      "loss": 1.0098,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.915795372442334,
+      "learning_rate": 4.587155963302753e-06,
+      "loss": 0.9699,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.0202263157289146,
+      "learning_rate": 5.504587155963303e-06,
+      "loss": 0.987,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.941819185301855,
+      "learning_rate": 6.422018348623854e-06,
+      "loss": 0.973,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.3388431226160704,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.9786,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.977546667798474,
+      "learning_rate": 8.256880733944956e-06,
+      "loss": 0.9682,
+      "step": 45
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.1514922297341688,
+      "learning_rate": 9.174311926605506e-06,
+      "loss": 0.9655,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.000399665458361,
+      "learning_rate": 1.0091743119266055e-05,
+      "loss": 0.9764,
+      "step": 55
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.8927332401265788,
+      "learning_rate": 1.1009174311926607e-05,
+      "loss": 0.9827,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.518457316528633,
+      "learning_rate": 1.1926605504587156e-05,
+      "loss": 0.9916,
+      "step": 65
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.8795240926276715,
+      "learning_rate": 1.2844036697247708e-05,
+      "loss": 0.978,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.4935356013821566,
+      "learning_rate": 1.3761467889908258e-05,
+      "loss": 0.9766,
+      "step": 75
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.466277593115983,
+      "learning_rate": 1.4678899082568809e-05,
+      "loss": 0.9745,
+      "step": 80
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.8668548628472559,
+      "learning_rate": 1.559633027522936e-05,
+      "loss": 0.9923,
+      "step": 85
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.97992788018359,
+      "learning_rate": 1.6513761467889912e-05,
+      "loss": 0.9952,
+      "step": 90
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.9211900138296392,
+      "learning_rate": 1.743119266055046e-05,
+      "loss": 1.0061,
+      "step": 95
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.0439374947928624,
+      "learning_rate": 1.834862385321101e-05,
+      "loss": 0.9985,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.484664541196989,
+      "learning_rate": 1.9266055045871563e-05,
+      "loss": 0.991,
+      "step": 105
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.207570653291085,
+      "learning_rate": 1.999994872196626e-05,
+      "loss": 1.002,
+      "step": 110
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.3955711863042564,
+      "learning_rate": 1.9998154046002822e-05,
+      "loss": 0.9923,
+      "step": 115
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.805464967586267,
+      "learning_rate": 1.999379599421534e-05,
+      "loss": 1.0008,
+      "step": 120
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.0096429770798974,
+      "learning_rate": 1.9986875683942535e-05,
+      "loss": 1.0239,
+      "step": 125
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.0670945338079534,
+      "learning_rate": 1.9977394889447526e-05,
+      "loss": 1.0025,
+      "step": 130
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.9796306144816491,
+      "learning_rate": 1.9965356041462954e-05,
+      "loss": 1.0148,
+      "step": 135
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.7112414903007187,
+      "learning_rate": 1.9950762226567783e-05,
+      "loss": 1.0019,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.997309626939832,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 0.9996,
+      "step": 145
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.0837540997070243,
+      "learning_rate": 1.9913925316676946e-05,
+      "loss": 1.0029,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 1.7532309300779665,
+      "learning_rate": 1.9891691666109112e-05,
+      "loss": 0.9814,
+      "step": 155
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.0488547177100593,
+      "learning_rate": 1.9866921935064907e-05,
+      "loss": 1.0033,
+      "step": 160
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.9186897481938363,
+      "learning_rate": 1.9839622474129595e-05,
+      "loss": 0.9948,
+      "step": 165
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.8790404004659207,
+      "learning_rate": 1.9809800282473014e-05,
+      "loss": 1.0133,
+      "step": 170
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.7611301480055446,
+      "learning_rate": 1.977746300605507e-05,
+      "loss": 1.0155,
+      "step": 175
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.836819737668185,
+      "learning_rate": 1.9742618935665478e-05,
+      "loss": 1.0041,
+      "step": 180
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.789300774084455,
+      "learning_rate": 1.9705277004798072e-05,
+      "loss": 1.0166,
+      "step": 185
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 242.96131281501275,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 4.2595,
+      "step": 190
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 109.15370345648675,
+      "learning_rate": 1.9623138495219292e-05,
+      "loss": 8.5047,
+      "step": 195
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 14.326179300350288,
+      "learning_rate": 1.957836297558229e-05,
+      "loss": 7.5663,
+      "step": 200
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 13.265654155079291,
+      "learning_rate": 1.9531131708217005e-05,
+      "loss": 7.3637,
+      "step": 205
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 13.674475954916327,
+      "learning_rate": 1.948145680250766e-05,
+      "loss": 7.273,
+      "step": 210
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 8.12456969902826,
+      "learning_rate": 1.9429350994350483e-05,
+      "loss": 7.2159,
+      "step": 215
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.6086468669712164,
+      "learning_rate": 1.93748276428884e-05,
+      "loss": 7.2198,
+      "step": 220
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 6.948446933409363,
+      "learning_rate": 1.931790072708596e-05,
+      "loss": 7.1902,
+      "step": 225
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.5376231155027646,
+      "learning_rate": 1.9258584842145342e-05,
+      "loss": 7.1989,
+      "step": 230
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.090167600205962,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 7.1904,
+      "step": 235
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.2600853909498593,
+      "learning_rate": 1.913284760423745e-05,
+      "loss": 7.1933,
+      "step": 240
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.819120975382211,
+      "learning_rate": 1.9066458488400586e-05,
+      "loss": 7.1664,
+      "step": 245
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 3.7632935964121224,
+      "learning_rate": 1.8997744869421248e-05,
+      "loss": 7.157,
+      "step": 250
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.633751035095585,
+      "learning_rate": 1.8926724364434447e-05,
+      "loss": 7.1275,
+      "step": 255
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.1750257818971965,
+      "learning_rate": 1.8853415182025953e-05,
+      "loss": 7.0982,
+      "step": 260
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.967324318899966,
+      "learning_rate": 1.8777836117563894e-05,
+      "loss": 7.0618,
+      "step": 265
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 19.315932042895618,
+      "learning_rate": 1.8700006548379898e-05,
+      "loss": 6.9764,
+      "step": 270
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 7.0881940447215666,
+      "learning_rate": 1.861994642880105e-05,
+      "loss": 6.9355,
+      "step": 275
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 22.552340976092317,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 6.8924,
+      "step": 280
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 35.955085580211176,
+      "learning_rate": 1.845321720990181e-05,
+      "loss": 6.8178,
+      "step": 285
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 44.03988221662733,
+      "learning_rate": 1.8366590857437182e-05,
+      "loss": 6.7881,
+      "step": 290
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 33.19644429475903,
+      "learning_rate": 1.8277819437329577e-05,
+      "loss": 6.7247,
+      "step": 295
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 73.6301202469884,
+      "learning_rate": 1.8186925709231534e-05,
+      "loss": 6.7,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 50.40805995123905,
+      "learning_rate": 1.809393297692334e-05,
+      "loss": 6.6299,
+      "step": 305
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 32.94909850757248,
+      "learning_rate": 1.799886508233829e-05,
+      "loss": 6.574,
+      "step": 310
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 58.62369850675989,
+      "learning_rate": 1.790174639944997e-05,
+      "loss": 6.5143,
+      "step": 315
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 58.028764013036465,
+      "learning_rate": 1.780260182802314e-05,
+      "loss": 6.4641,
+      "step": 320
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 177.84430268746536,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 6.4659,
+      "step": 325
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 55.12447286980276,
+      "learning_rate": 1.7598337209132142e-05,
+      "loss": 6.4537,
+      "step": 330
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 14.624403149302893,
+      "learning_rate": 1.7493269532033882e-05,
+      "loss": 6.4034,
+      "step": 335
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 43.70727416145112,
+      "learning_rate": 1.738628069370195e-05,
+      "loss": 6.3425,
+      "step": 340
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 51.61363762445518,
+      "learning_rate": 1.7277398124460022e-05,
+      "loss": 6.3135,
+      "step": 345
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 15.717786816672422,
+      "learning_rate": 1.71666497401558e-05,
+      "loss": 6.2447,
+      "step": 350
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 48.16105556797076,
+      "learning_rate": 1.7054063935003813e-05,
+      "loss": 6.2283,
+      "step": 355
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 45.33885455105297,
+      "learning_rate": 1.6939669574305565e-05,
+      "loss": 6.1934,
+      "step": 360
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 205.12275018145363,
+      "learning_rate": 1.6823495987048922e-05,
+      "loss": 6.1845,
+      "step": 365
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 140.34062856192622,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 6.1908,
+      "step": 370
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 22.719850989180927,
+      "learning_rate": 1.6585930722009602e-05,
+      "loss": 6.1466,
+      "step": 375
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 25.020898156050958,
+      "learning_rate": 1.6464599952375998e-05,
+      "loss": 6.1118,
+      "step": 380
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 29.78095814605391,
+      "learning_rate": 1.63416117568662e-05,
+      "loss": 6.0879,
+      "step": 385
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 27.691981481859912,
+      "learning_rate": 1.621699766779763e-05,
+      "loss": 6.035,
+      "step": 390
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 51.38905417037612,
+      "learning_rate": 1.6090789634342278e-05,
+      "loss": 6.0116,
+      "step": 395
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 56.33481087428632,
+      "learning_rate": 1.5963020014335437e-05,
+      "loss": 6.0081,
+      "step": 400
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 45.76341033354771,
+      "learning_rate": 1.583372156597961e-05,
+      "loss": 5.9674,
+      "step": 405
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 76.2485523686512,
+      "learning_rate": 1.570292743944583e-05,
+      "loss": 5.9338,
+      "step": 410
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 159.1246861661541,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 5.9722,
+      "step": 415
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 132.20908717790851,
+      "learning_rate": 1.5436986661277578e-05,
+      "loss": 5.9314,
+      "step": 420
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 71.6597882899901,
+      "learning_rate": 1.530190819284555e-05,
+      "loss": 5.9226,
+      "step": 425
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 24.57391536298703,
+      "learning_rate": 1.5165470395159314e-05,
+      "loss": 5.8777,
+      "step": 430
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 30.810204350884774,
+      "learning_rate": 1.5027708248811331e-05,
+      "loss": 5.8426,
+      "step": 435
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 22.007616074267528,
+      "learning_rate": 1.4888657073937077e-05,
+      "loss": 5.8248,
+      "step": 440
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 45.21451125526737,
+      "learning_rate": 1.4748352521159492e-05,
+      "loss": 5.8128,
+      "step": 445
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 66.1164622252545,
+      "learning_rate": 1.4606830562448692e-05,
+      "loss": 5.8,
+      "step": 450
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 66.43271019490362,
+      "learning_rate": 1.4464127481899312e-05,
+      "loss": 5.7388,
+      "step": 455
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 66.81215308290967,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 5.8021,
+      "step": 460
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 61.76469415155527,
+      "learning_rate": 1.4175324596392075e-05,
+      "loss": 5.7631,
+      "step": 465
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 65.59093203298633,
+      "learning_rate": 1.402929883613599e-05,
+      "loss": 5.736,
+      "step": 470
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 118.51044142323016,
+      "learning_rate": 1.3882240024460928e-05,
+      "loss": 5.6828,
+      "step": 475
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 105.84910737707047,
+      "learning_rate": 1.3734185865027061e-05,
+      "loss": 5.6849,
+      "step": 480
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 32.462567969669294,
+      "learning_rate": 1.358517431668672e-05,
+      "loss": 5.6538,
+      "step": 485
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 106.47382640656464,
+      "learning_rate": 1.3435243583752294e-05,
+      "loss": 5.6048,
+      "step": 490
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 145.1629065173643,
+      "learning_rate": 1.3284432106201233e-05,
+      "loss": 5.7145,
+      "step": 495
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 203.25513004760577,
+      "learning_rate": 1.313277854982062e-05,
+      "loss": 5.7344,
+      "step": 500
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 116.05723149181094,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 5.6577,
+      "step": 505
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 21.139566960386738,
+      "learning_rate": 1.2827100933231904e-05,
+      "loss": 5.6114,
+      "step": 510
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 26.813357095510124,
+      "learning_rate": 1.2673155244151985e-05,
+      "loss": 5.5589,
+      "step": 515
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 43.82656244521634,
+      "learning_rate": 1.2518524198405699e-05,
+      "loss": 5.5018,
+      "step": 520
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 65.3879946725387,
+      "learning_rate": 1.2363247441059775e-05,
+      "loss": 5.4885,
+      "step": 525
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 52.86165228521218,
+      "learning_rate": 1.2207364782731657e-05,
+      "loss": 5.4701,
+      "step": 530
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 59.44473618774632,
+      "learning_rate": 1.2050916189382646e-05,
+      "loss": 5.4302,
+      "step": 535
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 26.460703860460455,
+      "learning_rate": 1.189394177207125e-05,
+      "loss": 5.3781,
+      "step": 540
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 58.18972877786887,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 5.3572,
+      "step": 545
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 83.35921782852613,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 5.4269,
+      "step": 550
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 34.129434276568325,
+      "learning_rate": 1.1420266647205232e-05,
+      "loss": 5.364,
+      "step": 555
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 56.68082962283742,
+      "learning_rate": 1.1261592585930576e-05,
+      "loss": 5.2992,
+      "step": 560
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 21.643023682782022,
+      "learning_rate": 1.1102595071354471e-05,
+      "loss": 5.2592,
+      "step": 565
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 36.88815009730958,
+      "learning_rate": 1.0943314868040365e-05,
+      "loss": 5.2248,
+      "step": 570
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 35.31299501129291,
+      "learning_rate": 1.0783792813028828e-05,
+      "loss": 5.1845,
+      "step": 575
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 61.64543240010987,
+      "learning_rate": 1.0624069805367558e-05,
+      "loss": 5.2092,
+      "step": 580
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 32.919556730268106,
+      "learning_rate": 1.0464186795625481e-05,
+      "loss": 5.1762,
+      "step": 585
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 26.906436582456134,
+      "learning_rate": 1.0304184775393642e-05,
+      "loss": 5.1519,
+      "step": 590
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 48.66053797078755,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 5.1177,
+      "step": 595
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 56.3116146779967,
+      "learning_rate": 9.983987811869863e-06,
+      "loss": 5.102,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 87.9740004930047,
+      "learning_rate": 9.823874962247565e-06,
+      "loss": 5.1095,
+      "step": 605
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 66.31383230719314,
+      "learning_rate": 9.663807268427197e-06,
+      "loss": 5.1331,
+      "step": 610
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 58.69537097341761,
+      "learning_rate": 9.503825769350016e-06,
+      "loss": 5.0607,
+      "step": 615
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 50.77744089682505,
+      "learning_rate": 9.343971481858246e-06,
+      "loss": 5.0193,
+      "step": 620
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 40.26196176853548,
+      "learning_rate": 9.184285390178978e-06,
+      "loss": 4.9987,
+      "step": 625
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 37.04233592367474,
+      "learning_rate": 9.024808435416435e-06,
+      "loss": 4.99,
+      "step": 630
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 34.99570481216453,
+      "learning_rate": 8.865581505055292e-06,
+      "loss": 4.9782,
+      "step": 635
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 25.433787904984356,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 4.9216,
+      "step": 640
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 30.120360546905527,
+      "learning_rate": 8.548040936496989e-06,
+      "loss": 4.9355,
+      "step": 645
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 17.059498258803476,
+      "learning_rate": 8.389808710909881e-06,
+      "loss": 4.9029,
+      "step": 650
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 43.200600750978815,
+      "learning_rate": 8.231989314071318e-06,
+      "loss": 4.9199,
+      "step": 655
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 36.280085935407776,
+      "learning_rate": 8.07462320849313e-06,
+      "loss": 4.8689,
+      "step": 660
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 43.88644104874169,
+      "learning_rate": 7.917750740470116e-06,
+      "loss": 4.8891,
+      "step": 665
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 31.741053371313615,
+      "learning_rate": 7.761412129735853e-06,
+      "loss": 4.8543,
+      "step": 670
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 67.90017223502674,
+      "learning_rate": 7.605647459150961e-06,
+      "loss": 4.8095,
+      "step": 675
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 35.90719699243417,
+      "learning_rate": 7.4504966644264775e-06,
+      "loss": 4.8115,
+      "step": 680
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 39.02489729571871,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 4.8148,
+      "step": 685
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 46.142215188761334,
+      "learning_rate": 7.142195648261747e-06,
+      "loss": 4.8305,
+      "step": 690
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 25.914087667720942,
+      "learning_rate": 6.989124470549746e-06,
+      "loss": 4.7909,
+      "step": 695
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 35.254452574603874,
+      "learning_rate": 6.83682523588902e-06,
+      "loss": 4.7567,
+      "step": 700
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 51.24311260833751,
+      "learning_rate": 6.685336991505122e-06,
+      "loss": 4.7621,
+      "step": 705
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 62.972857231438994,
+      "learning_rate": 6.5346985766979384e-06,
+      "loss": 4.7508,
+      "step": 710
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 26.803155155590026,
+      "learning_rate": 6.384948612883872e-06,
+      "loss": 4.7262,
+      "step": 715
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 62.01432381157656,
+      "learning_rate": 6.2361254936939e-06,
+      "loss": 4.7213,
+      "step": 720
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 52.16714069263354,
+      "learning_rate": 6.0882673751300235e-06,
+      "loss": 4.7201,
+      "step": 725
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 47.197837362961145,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 4.6971,
+      "step": 730
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 52.802764515881336,
+      "learning_rate": 5.79559751711138e-06,
+      "loss": 4.6844,
+      "step": 735
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 40.805066320948455,
+      "learning_rate": 5.650860813791786e-06,
+      "loss": 4.6628,
+      "step": 740
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 46.63291056024256,
+      "learning_rate": 5.507239164130501e-06,
+      "loss": 4.6673,
+      "step": 745
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 25.617868108401684,
+      "learning_rate": 5.364769390551225e-06,
+      "loss": 4.6606,
+      "step": 750
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 30.046819543783922,
+      "learning_rate": 5.223488020154028e-06,
+      "loss": 4.6283,
+      "step": 755
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 29.92322960237207,
+      "learning_rate": 5.083431275350312e-06,
+      "loss": 4.6158,
+      "step": 760
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 23.14008510014771,
+      "learning_rate": 4.9446350645759885e-06,
+      "loss": 4.5927,
+      "step": 765
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 28.386364075607865,
+      "learning_rate": 4.807134973085036e-06,
+      "loss": 4.6146,
+      "step": 770
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 58.55131000208054,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 4.6026,
+      "step": 775
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 73.54411177838821,
+      "learning_rate": 4.53616381840377e-06,
+      "loss": 4.5888,
+      "step": 780
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 40.62402827270361,
+      "learning_rate": 4.402762228128531e-06,
+      "loss": 4.6271,
+      "step": 785
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 51.502712788137366,
+      "learning_rate": 4.270795685155001e-06,
+      "loss": 4.569,
+      "step": 790
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 27.330225371915265,
+      "learning_rate": 4.140298023713416e-06,
+      "loss": 4.5708,
+      "step": 795
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 21.99456795475846,
+      "learning_rate": 4.0113027014349374e-06,
+      "loss": 4.5624,
+      "step": 800
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 20.119033858069777,
+      "learning_rate": 3.883842790773647e-06,
+      "loss": 4.5602,
+      "step": 805
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 24.920824482756828,
+      "learning_rate": 3.757950970527249e-06,
+      "loss": 4.5386,
+      "step": 810
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 20.182025561534093,
+      "learning_rate": 3.633659517458736e-06,
+      "loss": 4.5425,
+      "step": 815
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 28.03996832003451,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 4.5275,
+      "step": 820
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 24.852500986861678,
+      "learning_rate": 3.39000476018726e-06,
+      "loss": 4.5516,
+      "step": 825
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 24.988158701271594,
+      "learning_rate": 3.2707039253872796e-06,
+      "loss": 4.5281,
+      "step": 830
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 17.31035723167651,
+      "learning_rate": 3.153128380554941e-06,
+      "loss": 4.5368,
+      "step": 835
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 29.648896729425456,
+      "learning_rate": 3.037308270285709e-06,
+      "loss": 4.4975,
+      "step": 840
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 24.46394840808864,
+      "learning_rate": 2.923273289108115e-06,
+      "loss": 4.4996,
+      "step": 845
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 22.621059381964272,
+      "learning_rate": 2.8110526738705345e-06,
+      "loss": 4.4796,
+      "step": 850
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 21.20489787284271,
+      "learning_rate": 2.700675196245288e-06,
+      "loss": 4.4752,
+      "step": 855
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 18.493488247322375,
+      "learning_rate": 2.592169155352031e-06,
+      "loss": 4.4879,
+      "step": 860
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 18.595132565936982,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 4.4689,
+      "step": 865
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 15.570886966815687,
+      "learning_rate": 2.3808821740669608e-06,
+      "loss": 4.4792,
+      "step": 870
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 19.069241841201656,
+      "learning_rate": 2.2781554044688015e-06,
+      "loss": 4.4739,
+      "step": 875
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 16.54384612167649,
+      "learning_rate": 2.1774083993013715e-06,
+      "loss": 4.4745,
+      "step": 880
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 20.19537097527119,
+      "learning_rate": 2.0786669885765044e-06,
+      "loss": 4.4725,
+      "step": 885
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 14.39041053114573,
+      "learning_rate": 1.981956488101898e-06,
+      "loss": 4.4684,
+      "step": 890
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 20.220456531856506,
+      "learning_rate": 1.8873016929904942e-06,
+      "loss": 4.4534,
+      "step": 895
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 27.77026468910616,
+      "learning_rate": 1.7947268713034128e-06,
+      "loss": 4.4627,
+      "step": 900
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 28.465744903023698,
+      "learning_rate": 1.704255757827963e-06,
+      "loss": 4.4307,
+      "step": 905
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 25.002218509146623,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 4.4409,
+      "step": 910
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 15.71265485425737,
+      "learning_rate": 1.529716891919074e-06,
+      "loss": 4.4379,
+      "step": 915
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 14.402869444397375,
+      "learning_rate": 1.4456938886170413e-06,
+      "loss": 4.4058,
+      "step": 920
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 16.403877600978255,
+      "learning_rate": 1.3638640803164516e-06,
+      "loss": 4.4251,
+      "step": 925
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 13.446090650346864,
+      "learning_rate": 1.2842484469453365e-06,
+      "loss": 4.4229,
+      "step": 930
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 14.466447190381347,
+      "learning_rate": 1.2068674007506787e-06,
+      "loss": 4.4321,
+      "step": 935
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 14.052171577869647,
+      "learning_rate": 1.1317407810650372e-06,
+      "loss": 4.4196,
+      "step": 940
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 18.473477215309615,
+      "learning_rate": 1.0588878492200261e-06,
+      "loss": 4.4253,
+      "step": 945
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 19.954808882391053,
+      "learning_rate": 9.883272836080116e-07,
+      "loss": 4.4108,
+      "step": 950
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 14.033845271160311,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 4.4486,
+      "step": 955
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 21.390405932058453,
+      "learning_rate": 8.541550213737171e-07,
+      "loss": 4.4044,
+      "step": 960
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 11.550215082840605,
+      "learning_rate": 7.905777244947954e-07,
+      "loss": 4.4409,
+      "step": 965
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 13.607796114151936,
+      "learning_rate": 7.293615845160196e-07,
+      "loss": 4.3938,
+      "step": 970
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 9.994454732482547,
+      "learning_rate": 6.705222963319191e-07,
+      "loss": 4.3996,
+      "step": 975
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 11.575017099126718,
+      "learning_rate": 6.140749454480932e-07,
+      "loss": 4.4276,
+      "step": 980
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 10.374432351937589,
+      "learning_rate": 5.600340041135133e-07,
+      "loss": 4.4383,
+      "step": 985
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 12.772375916116722,
+      "learning_rate": 5.0841332761005e-07,
+      "loss": 4.4046,
+      "step": 990
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 14.043876323714166,
+      "learning_rate": 4.592261507001994e-07,
+      "loss": 4.4136,
+      "step": 995
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 10.7144239108995,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 4.4157,
+      "step": 1000
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 9.84410027507594,
+      "learning_rate": 3.6820211191520127e-07,
+      "loss": 4.3885,
+      "step": 1005
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 8.571874802816026,
+      "learning_rate": 3.263885872300343e-07,
+      "loss": 4.4265,
+      "step": 1010
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 10.780577259685115,
+      "learning_rate": 2.870552305351382e-07,
+      "loss": 4.3938,
+      "step": 1015
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 11.893503141163247,
+      "learning_rate": 2.5021212630962246e-07,
+      "loss": 4.3798,
+      "step": 1020
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 9.062984025133662,
+      "learning_rate": 2.158687205694443e-07,
+      "loss": 4.3937,
+      "step": 1025
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 8.219330068607992,
+      "learning_rate": 1.840338184455881e-07,
+      "loss": 4.3905,
+      "step": 1030
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 7.246539185596847,
+      "learning_rate": 1.5471558192656776e-07,
+      "loss": 4.3864,
+      "step": 1035
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 7.0125806843462195,
+      "learning_rate": 1.279215277658097e-07,
+      "loss": 4.413,
+      "step": 1040
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 9.201800725889436,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 4.3679,
+      "step": 1045
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 7.076465448219673,
+      "learning_rate": 8.19327959602012e-08,
+      "loss": 4.3443,
+      "step": 1050
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 9.294237620575574,
+      "learning_rate": 6.274990913221035e-08,
+      "loss": 4.4186,
+      "step": 1055
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 5.94300131392314,
+      "learning_rate": 4.6114783273213395e-08,
+      "loss": 4.3711,
+      "step": 1060
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 7.1587345473456905,
+      "learning_rate": 3.203168337845508e-08,
+      "loss": 4.3909,
+      "step": 1065
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 8.342809351726451,
+      "learning_rate": 2.05042201422323e-08,
+      "loss": 4.3894,
+      "step": 1070
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 8.363435905130084,
+      "learning_rate": 1.1535349032167908e-08,
+      "loss": 4.3886,
+      "step": 1075
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 7.728421631832789,
+      "learning_rate": 5.127369531473525e-09,
+      "loss": 4.3824,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.285020285775841,
+      "learning_rate": 1.2819245493955746e-09,
+      "loss": 4.4253,
+      "step": 1085
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.94654446727408,
+      "learning_rate": 0.0,
+      "loss": 4.3906,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.393316268920898,
+      "eval_runtime": 332.2559,
+      "eval_samples_per_second": 46.443,
+      "eval_steps_per_second": 0.728,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "step": 1090,
+      "total_flos": 456447649382400.0,
+      "train_loss": 4.5692141799751775,
+      "train_runtime": 12438.5839,
+      "train_samples_per_second": 11.209,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "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
+}