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: 0.9366
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9201        | 1.0   | 1090 | 0.9366          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.1.0a0+32f93b1
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 456447649382400.0,
+    "train_loss": 0.9783915571116526,
+    "train_runtime": 14076.1137,
+    "train_samples": 207864,
+    "train_samples_per_second": 9.905,
+    "train_steps_per_second": 0.077
+}

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 sha256:7eecdc50fe0e20df05eb75e44a0d0dcbeefa3c855818f71ed6df3b9ef5a97dca
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b96e2617e884baf2fcbf54145651c12b30a5f2bc8be12c20e9528dfcd9ae6c
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c4ca66dec6b94f8611b692dd2133896c87fb9fb2a099cbe19ad5ca9f3b7a17
+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"
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 456447649382400.0,
+    "train_loss": 0.9783915571116526,
+    "train_runtime": 14076.1137,
+    "train_samples": 207864,
+    "train_samples_per_second": 9.905,
+    "train_steps_per_second": 0.077
+}

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": 8.590026968869019,
+      "learning_rate": 1.8348623853211012e-07,
+      "loss": 1.1365,
+      "step": 1
+    },
+    {
+      "epoch": 0.0045871559633027525,
+      "grad_norm": 7.486574820466339,
+      "learning_rate": 9.174311926605506e-07,
+      "loss": 1.1311,
+      "step": 5
+    },
+    {
+      "epoch": 0.009174311926605505,
+      "grad_norm": 4.039589713379416,
+      "learning_rate": 1.8348623853211011e-06,
+      "loss": 1.0455,
+      "step": 10
+    },
+    {
+      "epoch": 0.013761467889908258,
+      "grad_norm": 3.7172848594571635,
+      "learning_rate": 2.7522935779816517e-06,
+      "loss": 1.0276,
+      "step": 15
+    },
+    {
+      "epoch": 0.01834862385321101,
+      "grad_norm": 2.6728393178954097,
+      "learning_rate": 3.6697247706422022e-06,
+      "loss": 0.9965,
+      "step": 20
+    },
+    {
+      "epoch": 0.022935779816513763,
+      "grad_norm": 2.1111759195076383,
+      "learning_rate": 4.587155963302753e-06,
+      "loss": 0.9946,
+      "step": 25
+    },
+    {
+      "epoch": 0.027522935779816515,
+      "grad_norm": 2.2065873188991474,
+      "learning_rate": 5.504587155963303e-06,
+      "loss": 0.9918,
+      "step": 30
+    },
+    {
+      "epoch": 0.03211009174311927,
+      "grad_norm": 2.3927751227272838,
+      "learning_rate": 6.422018348623854e-06,
+      "loss": 0.9876,
+      "step": 35
+    },
+    {
+      "epoch": 0.03669724770642202,
+      "grad_norm": 2.198198830881205,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.9949,
+      "step": 40
+    },
+    {
+      "epoch": 0.04128440366972477,
+      "grad_norm": 2.3775388175981913,
+      "learning_rate": 8.256880733944956e-06,
+      "loss": 0.9785,
+      "step": 45
+    },
+    {
+      "epoch": 0.045871559633027525,
+      "grad_norm": 2.3636192230061694,
+      "learning_rate": 9.174311926605506e-06,
+      "loss": 0.9851,
+      "step": 50
+    },
+    {
+      "epoch": 0.05045871559633028,
+      "grad_norm": 2.551773091121245,
+      "learning_rate": 1.0091743119266055e-05,
+      "loss": 0.9935,
+      "step": 55
+    },
+    {
+      "epoch": 0.05504587155963303,
+      "grad_norm": 2.075016097277958,
+      "learning_rate": 1.1009174311926607e-05,
+      "loss": 0.9969,
+      "step": 60
+    },
+    {
+      "epoch": 0.05963302752293578,
+      "grad_norm": 2.288649040057403,
+      "learning_rate": 1.1926605504587156e-05,
+      "loss": 0.98,
+      "step": 65
+    },
+    {
+      "epoch": 0.06422018348623854,
+      "grad_norm": 2.7581294894600163,
+      "learning_rate": 1.2844036697247708e-05,
+      "loss": 0.9864,
+      "step": 70
+    },
+    {
+      "epoch": 0.06880733944954129,
+      "grad_norm": 2.727748671508115,
+      "learning_rate": 1.3761467889908258e-05,
+      "loss": 0.9998,
+      "step": 75
+    },
+    {
+      "epoch": 0.07339449541284404,
+      "grad_norm": 2.513424527269286,
+      "learning_rate": 1.4678899082568809e-05,
+      "loss": 0.9892,
+      "step": 80
+    },
+    {
+      "epoch": 0.0779816513761468,
+      "grad_norm": 2.0479456147390644,
+      "learning_rate": 1.559633027522936e-05,
+      "loss": 0.9927,
+      "step": 85
+    },
+    {
+      "epoch": 0.08256880733944955,
+      "grad_norm": 2.0867568861039487,
+      "learning_rate": 1.6513761467889912e-05,
+      "loss": 1.0121,
+      "step": 90
+    },
+    {
+      "epoch": 0.0871559633027523,
+      "grad_norm": 2.8827900604302603,
+      "learning_rate": 1.743119266055046e-05,
+      "loss": 1.0201,
+      "step": 95
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 2.0709329055230112,
+      "learning_rate": 1.834862385321101e-05,
+      "loss": 0.996,
+      "step": 100
+    },
+    {
+      "epoch": 0.0963302752293578,
+      "grad_norm": 2.5702081185928103,
+      "learning_rate": 1.9266055045871563e-05,
+      "loss": 1.0116,
+      "step": 105
+    },
+    {
+      "epoch": 0.10091743119266056,
+      "grad_norm": 2.1947935409816486,
+      "learning_rate": 1.999994872196626e-05,
+      "loss": 1.0224,
+      "step": 110
+    },
+    {
+      "epoch": 0.10550458715596331,
+      "grad_norm": 1.9964111903602946,
+      "learning_rate": 1.9998154046002822e-05,
+      "loss": 1.0057,
+      "step": 115
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 1.8945144621768437,
+      "learning_rate": 1.999379599421534e-05,
+      "loss": 1.0062,
+      "step": 120
+    },
+    {
+      "epoch": 0.11467889908256881,
+      "grad_norm": 1.8242468916557006,
+      "learning_rate": 1.9986875683942535e-05,
+      "loss": 1.0154,
+      "step": 125
+    },
+    {
+      "epoch": 0.11926605504587157,
+      "grad_norm": 1.8529020549594846,
+      "learning_rate": 1.9977394889447526e-05,
+      "loss": 1.0127,
+      "step": 130
+    },
+    {
+      "epoch": 0.12385321100917432,
+      "grad_norm": 1.8387109925666045,
+      "learning_rate": 1.9965356041462954e-05,
+      "loss": 0.9942,
+      "step": 135
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 2.0279915275712623,
+      "learning_rate": 1.9950762226567783e-05,
+      "loss": 1.0222,
+      "step": 140
+    },
+    {
+      "epoch": 0.13302752293577982,
+      "grad_norm": 2.1108737110478994,
+      "learning_rate": 1.9933617186395917e-05,
+      "loss": 1.0291,
+      "step": 145
+    },
+    {
+      "epoch": 0.13761467889908258,
+      "grad_norm": 2.1293431381675427,
+      "learning_rate": 1.9913925316676946e-05,
+      "loss": 1.0215,
+      "step": 150
+    },
+    {
+      "epoch": 0.14220183486238533,
+      "grad_norm": 1.9622943928954406,
+      "learning_rate": 1.9891691666109112e-05,
+      "loss": 1.0447,
+      "step": 155
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 1.9552108684711231,
+      "learning_rate": 1.9866921935064907e-05,
+      "loss": 1.034,
+      "step": 160
+    },
+    {
+      "epoch": 0.15137614678899083,
+      "grad_norm": 1.9190740305620202,
+      "learning_rate": 1.9839622474129595e-05,
+      "loss": 1.0446,
+      "step": 165
+    },
+    {
+      "epoch": 0.1559633027522936,
+      "grad_norm": 1.8020873014525902,
+      "learning_rate": 1.9809800282473014e-05,
+      "loss": 1.0322,
+      "step": 170
+    },
+    {
+      "epoch": 0.16055045871559634,
+      "grad_norm": 1.6996799547703936,
+      "learning_rate": 1.977746300605507e-05,
+      "loss": 1.0383,
+      "step": 175
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 2.187092931511103,
+      "learning_rate": 1.9742618935665478e-05,
+      "loss": 1.0294,
+      "step": 180
+    },
+    {
+      "epoch": 0.16972477064220184,
+      "grad_norm": 2.0403921365189963,
+      "learning_rate": 1.9705277004798072e-05,
+      "loss": 1.0349,
+      "step": 185
+    },
+    {
+      "epoch": 0.1743119266055046,
+      "grad_norm": 1.8496031208738504,
+      "learning_rate": 1.9665446787360444e-05,
+      "loss": 1.0404,
+      "step": 190
+    },
+    {
+      "epoch": 0.17889908256880735,
+      "grad_norm": 1.8823992627267585,
+      "learning_rate": 1.9623138495219292e-05,
+      "loss": 1.0209,
+      "step": 195
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 2.095822495179804,
+      "learning_rate": 1.957836297558229e-05,
+      "loss": 1.0222,
+      "step": 200
+    },
+    {
+      "epoch": 0.18807339449541285,
+      "grad_norm": 2.4911998482939355,
+      "learning_rate": 1.9531131708217005e-05,
+      "loss": 1.027,
+      "step": 205
+    },
+    {
+      "epoch": 0.1926605504587156,
+      "grad_norm": 1.821496874433616,
+      "learning_rate": 1.948145680250766e-05,
+      "loss": 1.0231,
+      "step": 210
+    },
+    {
+      "epoch": 0.19724770642201836,
+      "grad_norm": 1.759877910585677,
+      "learning_rate": 1.9429350994350483e-05,
+      "loss": 1.0345,
+      "step": 215
+    },
+    {
+      "epoch": 0.2018348623853211,
+      "grad_norm": 1.8748142613908458,
+      "learning_rate": 1.93748276428884e-05,
+      "loss": 1.0408,
+      "step": 220
+    },
+    {
+      "epoch": 0.20642201834862386,
+      "grad_norm": 2.0102856321068514,
+      "learning_rate": 1.931790072708596e-05,
+      "loss": 1.0245,
+      "step": 225
+    },
+    {
+      "epoch": 0.21100917431192662,
+      "grad_norm": 1.8044235525523873,
+      "learning_rate": 1.9258584842145342e-05,
+      "loss": 1.0434,
+      "step": 230
+    },
+    {
+      "epoch": 0.21559633027522937,
+      "grad_norm": 2.1107770756344193,
+      "learning_rate": 1.9196895195764363e-05,
+      "loss": 1.0216,
+      "step": 235
+    },
+    {
+      "epoch": 0.22018348623853212,
+      "grad_norm": 1.7741183736117787,
+      "learning_rate": 1.913284760423745e-05,
+      "loss": 1.0259,
+      "step": 240
+    },
+    {
+      "epoch": 0.22477064220183487,
+      "grad_norm": 1.8121132100517001,
+      "learning_rate": 1.9066458488400586e-05,
+      "loss": 1.0249,
+      "step": 245
+    },
+    {
+      "epoch": 0.22935779816513763,
+      "grad_norm": 1.6374262690884738,
+      "learning_rate": 1.8997744869421248e-05,
+      "loss": 1.02,
+      "step": 250
+    },
+    {
+      "epoch": 0.23394495412844038,
+      "grad_norm": 1.7269378718345392,
+      "learning_rate": 1.8926724364434447e-05,
+      "loss": 1.013,
+      "step": 255
+    },
+    {
+      "epoch": 0.23853211009174313,
+      "grad_norm": 1.7554961488227134,
+      "learning_rate": 1.8853415182025953e-05,
+      "loss": 1.0275,
+      "step": 260
+    },
+    {
+      "epoch": 0.24311926605504589,
+      "grad_norm": 1.888907283355598,
+      "learning_rate": 1.8777836117563894e-05,
+      "loss": 1.0307,
+      "step": 265
+    },
+    {
+      "epoch": 0.24770642201834864,
+      "grad_norm": 1.6943826060007061,
+      "learning_rate": 1.8700006548379898e-05,
+      "loss": 1.021,
+      "step": 270
+    },
+    {
+      "epoch": 0.25229357798165136,
+      "grad_norm": 1.622531543885841,
+      "learning_rate": 1.861994642880105e-05,
+      "loss": 1.0392,
+      "step": 275
+    },
+    {
+      "epoch": 0.25688073394495414,
+      "grad_norm": 1.5095301144772582,
+      "learning_rate": 1.8537676285033886e-05,
+      "loss": 1.0279,
+      "step": 280
+    },
+    {
+      "epoch": 0.26146788990825687,
+      "grad_norm": 1.6417056350190902,
+      "learning_rate": 1.845321720990181e-05,
+      "loss": 1.0296,
+      "step": 285
+    },
+    {
+      "epoch": 0.26605504587155965,
+      "grad_norm": 1.5722941630740008,
+      "learning_rate": 1.8366590857437182e-05,
+      "loss": 1.0334,
+      "step": 290
+    },
+    {
+      "epoch": 0.2706422018348624,
+      "grad_norm": 1.8638842301102823,
+      "learning_rate": 1.8277819437329577e-05,
+      "loss": 1.0215,
+      "step": 295
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 1.63281187814375,
+      "learning_rate": 1.8186925709231534e-05,
+      "loss": 1.0341,
+      "step": 300
+    },
+    {
+      "epoch": 0.2798165137614679,
+      "grad_norm": 1.661078648257904,
+      "learning_rate": 1.809393297692334e-05,
+      "loss": 1.0246,
+      "step": 305
+    },
+    {
+      "epoch": 0.28440366972477066,
+      "grad_norm": 1.7482598431925447,
+      "learning_rate": 1.799886508233829e-05,
+      "loss": 1.0442,
+      "step": 310
+    },
+    {
+      "epoch": 0.2889908256880734,
+      "grad_norm": 1.577636868272626,
+      "learning_rate": 1.790174639944997e-05,
+      "loss": 1.0369,
+      "step": 315
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 1.7044142589762405,
+      "learning_rate": 1.780260182802314e-05,
+      "loss": 1.0239,
+      "step": 320
+    },
+    {
+      "epoch": 0.2981651376146789,
+      "grad_norm": 1.7546359102106406,
+      "learning_rate": 1.7701456787229805e-05,
+      "loss": 1.0327,
+      "step": 325
+    },
+    {
+      "epoch": 0.30275229357798167,
+      "grad_norm": 1.5039111648273473,
+      "learning_rate": 1.7598337209132142e-05,
+      "loss": 1.0157,
+      "step": 330
+    },
+    {
+      "epoch": 0.3073394495412844,
+      "grad_norm": 1.6602442070381076,
+      "learning_rate": 1.7493269532033882e-05,
+      "loss": 1.0182,
+      "step": 335
+    },
+    {
+      "epoch": 0.3119266055045872,
+      "grad_norm": 1.53831993823906,
+      "learning_rate": 1.738628069370195e-05,
+      "loss": 1.029,
+      "step": 340
+    },
+    {
+      "epoch": 0.3165137614678899,
+      "grad_norm": 1.6805290811393307,
+      "learning_rate": 1.7277398124460022e-05,
+      "loss": 1.0235,
+      "step": 345
+    },
+    {
+      "epoch": 0.3211009174311927,
+      "grad_norm": 1.4853849203076779,
+      "learning_rate": 1.71666497401558e-05,
+      "loss": 0.9925,
+      "step": 350
+    },
+    {
+      "epoch": 0.3256880733944954,
+      "grad_norm": 1.672232887496304,
+      "learning_rate": 1.7054063935003813e-05,
+      "loss": 1.0252,
+      "step": 355
+    },
+    {
+      "epoch": 0.3302752293577982,
+      "grad_norm": 1.6345254123456943,
+      "learning_rate": 1.6939669574305565e-05,
+      "loss": 1.0085,
+      "step": 360
+    },
+    {
+      "epoch": 0.3348623853211009,
+      "grad_norm": 1.5262133900432817,
+      "learning_rate": 1.6823495987048922e-05,
+      "loss": 1.0105,
+      "step": 365
+    },
+    {
+      "epoch": 0.3394495412844037,
+      "grad_norm": 1.5242935487304878,
+      "learning_rate": 1.6705572958388576e-05,
+      "loss": 1.0108,
+      "step": 370
+    },
+    {
+      "epoch": 0.3440366972477064,
+      "grad_norm": 1.6718301781389493,
+      "learning_rate": 1.6585930722009602e-05,
+      "loss": 1.0347,
+      "step": 375
+    },
+    {
+      "epoch": 0.3486238532110092,
+      "grad_norm": 1.4913729762956598,
+      "learning_rate": 1.6464599952375998e-05,
+      "loss": 1.0232,
+      "step": 380
+    },
+    {
+      "epoch": 0.3532110091743119,
+      "grad_norm": 1.5351597927925422,
+      "learning_rate": 1.63416117568662e-05,
+      "loss": 1.0177,
+      "step": 385
+    },
+    {
+      "epoch": 0.3577981651376147,
+      "grad_norm": 1.5623411713080309,
+      "learning_rate": 1.621699766779763e-05,
+      "loss": 1.0144,
+      "step": 390
+    },
+    {
+      "epoch": 0.3623853211009174,
+      "grad_norm": 1.4434170639068806,
+      "learning_rate": 1.6090789634342278e-05,
+      "loss": 1.005,
+      "step": 395
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 1.524722181019825,
+      "learning_rate": 1.5963020014335437e-05,
+      "loss": 1.0134,
+      "step": 400
+    },
+    {
+      "epoch": 0.37155963302752293,
+      "grad_norm": 1.5856120759168468,
+      "learning_rate": 1.583372156597961e-05,
+      "loss": 1.0059,
+      "step": 405
+    },
+    {
+      "epoch": 0.3761467889908257,
+      "grad_norm": 1.4415082474651109,
+      "learning_rate": 1.570292743944583e-05,
+      "loss": 1.0029,
+      "step": 410
+    },
+    {
+      "epoch": 0.38073394495412843,
+      "grad_norm": 1.4260675517472883,
+      "learning_rate": 1.557067116837444e-05,
+      "loss": 1.0219,
+      "step": 415
+    },
+    {
+      "epoch": 0.3853211009174312,
+      "grad_norm": 1.468487983706826,
+      "learning_rate": 1.5436986661277578e-05,
+      "loss": 1.013,
+      "step": 420
+    },
+    {
+      "epoch": 0.38990825688073394,
+      "grad_norm": 1.5254325276571765,
+      "learning_rate": 1.530190819284555e-05,
+      "loss": 1.0034,
+      "step": 425
+    },
+    {
+      "epoch": 0.3944954128440367,
+      "grad_norm": 1.5798795100356116,
+      "learning_rate": 1.5165470395159314e-05,
+      "loss": 1.0332,
+      "step": 430
+    },
+    {
+      "epoch": 0.39908256880733944,
+      "grad_norm": 1.552200364694848,
+      "learning_rate": 1.5027708248811331e-05,
+      "loss": 1.0007,
+      "step": 435
+    },
+    {
+      "epoch": 0.4036697247706422,
+      "grad_norm": 1.4214931631494656,
+      "learning_rate": 1.4888657073937077e-05,
+      "loss": 1.0094,
+      "step": 440
+    },
+    {
+      "epoch": 0.40825688073394495,
+      "grad_norm": 1.4843255397237436,
+      "learning_rate": 1.4748352521159492e-05,
+      "loss": 0.9961,
+      "step": 445
+    },
+    {
+      "epoch": 0.41284403669724773,
+      "grad_norm": 1.4632988494224077,
+      "learning_rate": 1.4606830562448692e-05,
+      "loss": 1.0058,
+      "step": 450
+    },
+    {
+      "epoch": 0.41743119266055045,
+      "grad_norm": 1.4953822979383466,
+      "learning_rate": 1.4464127481899312e-05,
+      "loss": 1.008,
+      "step": 455
+    },
+    {
+      "epoch": 0.42201834862385323,
+      "grad_norm": 1.4559315828564945,
+      "learning_rate": 1.4320279866427798e-05,
+      "loss": 1.0065,
+      "step": 460
+    },
+    {
+      "epoch": 0.42660550458715596,
+      "grad_norm": 1.6922761610390848,
+      "learning_rate": 1.4175324596392075e-05,
+      "loss": 1.0205,
+      "step": 465
+    },
+    {
+      "epoch": 0.43119266055045874,
+      "grad_norm": 1.590358388704108,
+      "learning_rate": 1.402929883613599e-05,
+      "loss": 1.0069,
+      "step": 470
+    },
+    {
+      "epoch": 0.43577981651376146,
+      "grad_norm": 1.4546641964451503,
+      "learning_rate": 1.3882240024460928e-05,
+      "loss": 0.9926,
+      "step": 475
+    },
+    {
+      "epoch": 0.44036697247706424,
+      "grad_norm": 1.4097757101446433,
+      "learning_rate": 1.3734185865027061e-05,
+      "loss": 1.0109,
+      "step": 480
+    },
+    {
+      "epoch": 0.44495412844036697,
+      "grad_norm": 1.4718695959287078,
+      "learning_rate": 1.358517431668672e-05,
+      "loss": 0.9992,
+      "step": 485
+    },
+    {
+      "epoch": 0.44954128440366975,
+      "grad_norm": 1.3849859496158945,
+      "learning_rate": 1.3435243583752294e-05,
+      "loss": 0.9943,
+      "step": 490
+    },
+    {
+      "epoch": 0.4541284403669725,
+      "grad_norm": 1.4115509115184626,
+      "learning_rate": 1.3284432106201233e-05,
+      "loss": 0.9882,
+      "step": 495
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 1.541052954984908,
+      "learning_rate": 1.313277854982062e-05,
+      "loss": 1.0081,
+      "step": 500
+    },
+    {
+      "epoch": 0.463302752293578,
+      "grad_norm": 1.6604691549617376,
+      "learning_rate": 1.2980321796293838e-05,
+      "loss": 0.9893,
+      "step": 505
+    },
+    {
+      "epoch": 0.46788990825688076,
+      "grad_norm": 1.5419924069079967,
+      "learning_rate": 1.2827100933231904e-05,
+      "loss": 1.005,
+      "step": 510
+    },
+    {
+      "epoch": 0.4724770642201835,
+      "grad_norm": 1.5391926952486923,
+      "learning_rate": 1.2673155244151985e-05,
+      "loss": 1.0106,
+      "step": 515
+    },
+    {
+      "epoch": 0.47706422018348627,
+      "grad_norm": 1.5041092670535134,
+      "learning_rate": 1.2518524198405699e-05,
+      "loss": 0.9993,
+      "step": 520
+    },
+    {
+      "epoch": 0.481651376146789,
+      "grad_norm": 1.5768343545674215,
+      "learning_rate": 1.2363247441059775e-05,
+      "loss": 0.9841,
+      "step": 525
+    },
+    {
+      "epoch": 0.48623853211009177,
+      "grad_norm": 1.4584802149012241,
+      "learning_rate": 1.2207364782731657e-05,
+      "loss": 1.0082,
+      "step": 530
+    },
+    {
+      "epoch": 0.4908256880733945,
+      "grad_norm": 1.428960359443167,
+      "learning_rate": 1.2050916189382646e-05,
+      "loss": 0.9731,
+      "step": 535
+    },
+    {
+      "epoch": 0.4954128440366973,
+      "grad_norm": 1.4606267386566858,
+      "learning_rate": 1.189394177207125e-05,
+      "loss": 0.9795,
+      "step": 540
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.376913229782971,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.9881,
+      "step": 545
+    },
+    {
+      "epoch": 0.5045871559633027,
+      "grad_norm": 1.3836549478959417,
+      "learning_rate": 1.1578576573543541e-05,
+      "loss": 0.9641,
+      "step": 550
+    },
+    {
+      "epoch": 0.5091743119266054,
+      "grad_norm": 1.356149707622323,
+      "learning_rate": 1.1420266647205232e-05,
+      "loss": 0.9744,
+      "step": 555
+    },
+    {
+      "epoch": 0.5137614678899083,
+      "grad_norm": 1.3827419350659662,
+      "learning_rate": 1.1261592585930576e-05,
+      "loss": 0.9839,
+      "step": 560
+    },
+    {
+      "epoch": 0.518348623853211,
+      "grad_norm": 1.4379779871173162,
+      "learning_rate": 1.1102595071354471e-05,
+      "loss": 0.9851,
+      "step": 565
+    },
+    {
+      "epoch": 0.5229357798165137,
+      "grad_norm": 1.399288614224523,
+      "learning_rate": 1.0943314868040365e-05,
+      "loss": 0.9781,
+      "step": 570
+    },
+    {
+      "epoch": 0.5275229357798165,
+      "grad_norm": 1.4412830988024221,
+      "learning_rate": 1.0783792813028828e-05,
+      "loss": 0.9881,
+      "step": 575
+    },
+    {
+      "epoch": 0.5321100917431193,
+      "grad_norm": 1.365677938278276,
+      "learning_rate": 1.0624069805367558e-05,
+      "loss": 0.9696,
+      "step": 580
+    },
+    {
+      "epoch": 0.536697247706422,
+      "grad_norm": 1.3825640573901334,
+      "learning_rate": 1.0464186795625481e-05,
+      "loss": 0.9726,
+      "step": 585
+    },
+    {
+      "epoch": 0.5412844036697247,
+      "grad_norm": 1.4955792558472396,
+      "learning_rate": 1.0304184775393642e-05,
+      "loss": 0.9874,
+      "step": 590
+    },
+    {
+      "epoch": 0.5458715596330275,
+      "grad_norm": 1.3824032912359923,
+      "learning_rate": 1.0144104766775574e-05,
+      "loss": 0.9695,
+      "step": 595
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 1.3477277386187514,
+      "learning_rate": 9.983987811869863e-06,
+      "loss": 0.9617,
+      "step": 600
+    },
+    {
+      "epoch": 0.555045871559633,
+      "grad_norm": 1.4036097176796005,
+      "learning_rate": 9.823874962247565e-06,
+      "loss": 0.9847,
+      "step": 605
+    },
+    {
+      "epoch": 0.5596330275229358,
+      "grad_norm": 1.4536087002525018,
+      "learning_rate": 9.663807268427197e-06,
+      "loss": 0.9493,
+      "step": 610
+    },
+    {
+      "epoch": 0.5642201834862385,
+      "grad_norm": 1.3938810806635806,
+      "learning_rate": 9.503825769350016e-06,
+      "loss": 0.9759,
+      "step": 615
+    },
+    {
+      "epoch": 0.5688073394495413,
+      "grad_norm": 1.4313464690072646,
+      "learning_rate": 9.343971481858246e-06,
+      "loss": 0.9718,
+      "step": 620
+    },
+    {
+      "epoch": 0.573394495412844,
+      "grad_norm": 1.3483789746433568,
+      "learning_rate": 9.184285390178978e-06,
+      "loss": 0.9685,
+      "step": 625
+    },
+    {
+      "epoch": 0.5779816513761468,
+      "grad_norm": 1.3437326617499212,
+      "learning_rate": 9.024808435416435e-06,
+      "loss": 0.9565,
+      "step": 630
+    },
+    {
+      "epoch": 0.5825688073394495,
+      "grad_norm": 1.3899537082883675,
+      "learning_rate": 8.865581505055292e-06,
+      "loss": 0.966,
+      "step": 635
+    },
+    {
+      "epoch": 0.5871559633027523,
+      "grad_norm": 1.4049970453901013,
+      "learning_rate": 8.706645422477739e-06,
+      "loss": 0.9609,
+      "step": 640
+    },
+    {
+      "epoch": 0.591743119266055,
+      "grad_norm": 1.563627127558928,
+      "learning_rate": 8.548040936496989e-06,
+      "loss": 0.9669,
+      "step": 645
+    },
+    {
+      "epoch": 0.5963302752293578,
+      "grad_norm": 1.4175659667522775,
+      "learning_rate": 8.389808710909881e-06,
+      "loss": 0.969,
+      "step": 650
+    },
+    {
+      "epoch": 0.6009174311926605,
+      "grad_norm": 1.3887375134393394,
+      "learning_rate": 8.231989314071318e-06,
+      "loss": 0.9672,
+      "step": 655
+    },
+    {
+      "epoch": 0.6055045871559633,
+      "grad_norm": 1.3886857636850283,
+      "learning_rate": 8.07462320849313e-06,
+      "loss": 0.9825,
+      "step": 660
+    },
+    {
+      "epoch": 0.6100917431192661,
+      "grad_norm": 1.3852031395838529,
+      "learning_rate": 7.917750740470116e-06,
+      "loss": 0.9612,
+      "step": 665
+    },
+    {
+      "epoch": 0.6146788990825688,
+      "grad_norm": 1.3564902677213335,
+      "learning_rate": 7.761412129735853e-06,
+      "loss": 0.9606,
+      "step": 670
+    },
+    {
+      "epoch": 0.6192660550458715,
+      "grad_norm": 1.364640541839942,
+      "learning_rate": 7.605647459150961e-06,
+      "loss": 0.9699,
+      "step": 675
+    },
+    {
+      "epoch": 0.6238532110091743,
+      "grad_norm": 1.3628791024834306,
+      "learning_rate": 7.4504966644264775e-06,
+      "loss": 0.9499,
+      "step": 680
+    },
+    {
+      "epoch": 0.6284403669724771,
+      "grad_norm": 1.3160716541619537,
+      "learning_rate": 7.295999523884921e-06,
+      "loss": 0.9605,
+      "step": 685
+    },
+    {
+      "epoch": 0.6330275229357798,
+      "grad_norm": 1.3601615038063317,
+      "learning_rate": 7.142195648261747e-06,
+      "loss": 0.9712,
+      "step": 690
+    },
+    {
+      "epoch": 0.6376146788990825,
+      "grad_norm": 1.3879140081588965,
+      "learning_rate": 6.989124470549746e-06,
+      "loss": 0.9397,
+      "step": 695
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 1.3184740100520171,
+      "learning_rate": 6.83682523588902e-06,
+      "loss": 0.9636,
+      "step": 700
+    },
+    {
+      "epoch": 0.6467889908256881,
+      "grad_norm": 1.3571390496693267,
+      "learning_rate": 6.685336991505122e-06,
+      "loss": 0.9661,
+      "step": 705
+    },
+    {
+      "epoch": 0.6513761467889908,
+      "grad_norm": 1.306435428954974,
+      "learning_rate": 6.5346985766979384e-06,
+      "loss": 0.9546,
+      "step": 710
+    },
+    {
+      "epoch": 0.6559633027522935,
+      "grad_norm": 1.3143087769244612,
+      "learning_rate": 6.384948612883872e-06,
+      "loss": 0.9599,
+      "step": 715
+    },
+    {
+      "epoch": 0.6605504587155964,
+      "grad_norm": 1.2717322661805426,
+      "learning_rate": 6.2361254936939e-06,
+      "loss": 0.9589,
+      "step": 720
+    },
+    {
+      "epoch": 0.6651376146788991,
+      "grad_norm": 1.304695248009233,
+      "learning_rate": 6.0882673751300235e-06,
+      "loss": 0.9477,
+      "step": 725
+    },
+    {
+      "epoch": 0.6697247706422018,
+      "grad_norm": 1.3414217532090449,
+      "learning_rate": 5.941412165782645e-06,
+      "loss": 0.9568,
+      "step": 730
+    },
+    {
+      "epoch": 0.6743119266055045,
+      "grad_norm": 1.4013089394139884,
+      "learning_rate": 5.79559751711138e-06,
+      "loss": 0.9482,
+      "step": 735
+    },
+    {
+      "epoch": 0.6788990825688074,
+      "grad_norm": 1.3044699444068533,
+      "learning_rate": 5.650860813791786e-06,
+      "loss": 0.9486,
+      "step": 740
+    },
+    {
+      "epoch": 0.6834862385321101,
+      "grad_norm": 1.3828781502865561,
+      "learning_rate": 5.507239164130501e-06,
+      "loss": 0.9489,
+      "step": 745
+    },
+    {
+      "epoch": 0.6880733944954128,
+      "grad_norm": 1.3314126321208273,
+      "learning_rate": 5.364769390551225e-06,
+      "loss": 0.969,
+      "step": 750
+    },
+    {
+      "epoch": 0.6926605504587156,
+      "grad_norm": 1.2942289271606044,
+      "learning_rate": 5.223488020154028e-06,
+      "loss": 0.96,
+      "step": 755
+    },
+    {
+      "epoch": 0.6972477064220184,
+      "grad_norm": 1.3357321457662634,
+      "learning_rate": 5.083431275350312e-06,
+      "loss": 0.9258,
+      "step": 760
+    },
+    {
+      "epoch": 0.7018348623853211,
+      "grad_norm": 1.3041211686044023,
+      "learning_rate": 4.9446350645759885e-06,
+      "loss": 0.9417,
+      "step": 765
+    },
+    {
+      "epoch": 0.7064220183486238,
+      "grad_norm": 1.380479241153724,
+      "learning_rate": 4.807134973085036e-06,
+      "loss": 0.9666,
+      "step": 770
+    },
+    {
+      "epoch": 0.7110091743119266,
+      "grad_norm": 1.2413378517127889,
+      "learning_rate": 4.670966253826027e-06,
+      "loss": 0.9352,
+      "step": 775
+    },
+    {
+      "epoch": 0.7155963302752294,
+      "grad_norm": 1.4796267075105034,
+      "learning_rate": 4.53616381840377e-06,
+      "loss": 0.9473,
+      "step": 780
+    },
+    {
+      "epoch": 0.7201834862385321,
+      "grad_norm": 1.3651275142718018,
+      "learning_rate": 4.402762228128531e-06,
+      "loss": 0.9392,
+      "step": 785
+    },
+    {
+      "epoch": 0.7247706422018348,
+      "grad_norm": 1.4100087288923597,
+      "learning_rate": 4.270795685155001e-06,
+      "loss": 0.9478,
+      "step": 790
+    },
+    {
+      "epoch": 0.7293577981651376,
+      "grad_norm": 1.3017707707123873,
+      "learning_rate": 4.140298023713416e-06,
+      "loss": 0.9301,
+      "step": 795
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 1.3267041246218492,
+      "learning_rate": 4.0113027014349374e-06,
+      "loss": 0.9146,
+      "step": 800
+    },
+    {
+      "epoch": 0.7385321100917431,
+      "grad_norm": 1.2995509569521342,
+      "learning_rate": 3.883842790773647e-06,
+      "loss": 0.9573,
+      "step": 805
+    },
+    {
+      "epoch": 0.7431192660550459,
+      "grad_norm": 1.2910745261862546,
+      "learning_rate": 3.757950970527249e-06,
+      "loss": 0.9265,
+      "step": 810
+    },
+    {
+      "epoch": 0.7477064220183486,
+      "grad_norm": 1.2853989305550235,
+      "learning_rate": 3.633659517458736e-06,
+      "loss": 0.9248,
+      "step": 815
+    },
+    {
+      "epoch": 0.7522935779816514,
+      "grad_norm": 1.263114329710996,
+      "learning_rate": 3.511000298021098e-06,
+      "loss": 0.9231,
+      "step": 820
+    },
+    {
+      "epoch": 0.7568807339449541,
+      "grad_norm": 1.3202969619364027,
+      "learning_rate": 3.39000476018726e-06,
+      "loss": 0.9265,
+      "step": 825
+    },
+    {
+      "epoch": 0.7614678899082569,
+      "grad_norm": 1.2837511661684693,
+      "learning_rate": 3.2707039253872796e-06,
+      "loss": 0.9238,
+      "step": 830
+    },
+    {
+      "epoch": 0.7660550458715596,
+      "grad_norm": 1.272334565345566,
+      "learning_rate": 3.153128380554941e-06,
+      "loss": 0.9318,
+      "step": 835
+    },
+    {
+      "epoch": 0.7706422018348624,
+      "grad_norm": 1.2911962822321414,
+      "learning_rate": 3.037308270285709e-06,
+      "loss": 0.9229,
+      "step": 840
+    },
+    {
+      "epoch": 0.7752293577981652,
+      "grad_norm": 1.2871010544124712,
+      "learning_rate": 2.923273289108115e-06,
+      "loss": 0.9409,
+      "step": 845
+    },
+    {
+      "epoch": 0.7798165137614679,
+      "grad_norm": 1.2957020048675643,
+      "learning_rate": 2.8110526738705345e-06,
+      "loss": 0.9243,
+      "step": 850
+    },
+    {
+      "epoch": 0.7844036697247706,
+      "grad_norm": 1.291643068745679,
+      "learning_rate": 2.700675196245288e-06,
+      "loss": 0.9396,
+      "step": 855
+    },
+    {
+      "epoch": 0.7889908256880734,
+      "grad_norm": 1.2442630476677876,
+      "learning_rate": 2.592169155352031e-06,
+      "loss": 0.9416,
+      "step": 860
+    },
+    {
+      "epoch": 0.7935779816513762,
+      "grad_norm": 1.2808835563133167,
+      "learning_rate": 2.485562370502279e-06,
+      "loss": 0.9428,
+      "step": 865
+    },
+    {
+      "epoch": 0.7981651376146789,
+      "grad_norm": 1.322945652372357,
+      "learning_rate": 2.3808821740669608e-06,
+      "loss": 0.9358,
+      "step": 870
+    },
+    {
+      "epoch": 0.8027522935779816,
+      "grad_norm": 1.3273655469543255,
+      "learning_rate": 2.2781554044688015e-06,
+      "loss": 0.9379,
+      "step": 875
+    },
+    {
+      "epoch": 0.8073394495412844,
+      "grad_norm": 1.2953684297066224,
+      "learning_rate": 2.1774083993013715e-06,
+      "loss": 0.935,
+      "step": 880
+    },
+    {
+      "epoch": 0.8119266055045872,
+      "grad_norm": 1.314047012294258,
+      "learning_rate": 2.0786669885765044e-06,
+      "loss": 0.9273,
+      "step": 885
+    },
+    {
+      "epoch": 0.8165137614678899,
+      "grad_norm": 1.2910450886812495,
+      "learning_rate": 1.981956488101898e-06,
+      "loss": 0.9406,
+      "step": 890
+    },
+    {
+      "epoch": 0.8211009174311926,
+      "grad_norm": 1.2889304700514808,
+      "learning_rate": 1.8873016929904942e-06,
+      "loss": 0.9423,
+      "step": 895
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 1.2584483146134866,
+      "learning_rate": 1.7947268713034128e-06,
+      "loss": 0.9119,
+      "step": 900
+    },
+    {
+      "epoch": 0.8302752293577982,
+      "grad_norm": 1.2306571475976114,
+      "learning_rate": 1.704255757827963e-06,
+      "loss": 0.9147,
+      "step": 905
+    },
+    {
+      "epoch": 0.8348623853211009,
+      "grad_norm": 1.2996923914258511,
+      "learning_rate": 1.6159115479924259e-06,
+      "loss": 0.9309,
+      "step": 910
+    },
+    {
+      "epoch": 0.8394495412844036,
+      "grad_norm": 1.3030591756269578,
+      "learning_rate": 1.529716891919074e-06,
+      "loss": 0.9393,
+      "step": 915
+    },
+    {
+      "epoch": 0.8440366972477065,
+      "grad_norm": 1.289888704070606,
+      "learning_rate": 1.4456938886170413e-06,
+      "loss": 0.9106,
+      "step": 920
+    },
+    {
+      "epoch": 0.8486238532110092,
+      "grad_norm": 1.3368041078863482,
+      "learning_rate": 1.3638640803164516e-06,
+      "loss": 0.9242,
+      "step": 925
+    },
+    {
+      "epoch": 0.8532110091743119,
+      "grad_norm": 1.2917360929177786,
+      "learning_rate": 1.2842484469453365e-06,
+      "loss": 0.9143,
+      "step": 930
+    },
+    {
+      "epoch": 0.8577981651376146,
+      "grad_norm": 1.2939657342934223,
+      "learning_rate": 1.2068674007506787e-06,
+      "loss": 0.9286,
+      "step": 935
+    },
+    {
+      "epoch": 0.8623853211009175,
+      "grad_norm": 1.3560403644461199,
+      "learning_rate": 1.1317407810650372e-06,
+      "loss": 0.9264,
+      "step": 940
+    },
+    {
+      "epoch": 0.8669724770642202,
+      "grad_norm": 1.2478045531537327,
+      "learning_rate": 1.0588878492200261e-06,
+      "loss": 0.9319,
+      "step": 945
+    },
+    {
+      "epoch": 0.8715596330275229,
+      "grad_norm": 1.2774964714280372,
+      "learning_rate": 9.883272836080116e-07,
+      "loss": 0.9195,
+      "step": 950
+    },
+    {
+      "epoch": 0.8761467889908257,
+      "grad_norm": 1.2810847178825988,
+      "learning_rate": 9.200771748932513e-07,
+      "loss": 0.9327,
+      "step": 955
+    },
+    {
+      "epoch": 0.8807339449541285,
+      "grad_norm": 1.300184919031024,
+      "learning_rate": 8.541550213737171e-07,
+      "loss": 0.9115,
+      "step": 960
+    },
+    {
+      "epoch": 0.8853211009174312,
+      "grad_norm": 1.2673226234465946,
+      "learning_rate": 7.905777244947954e-07,
+      "loss": 0.9182,
+      "step": 965
+    },
+    {
+      "epoch": 0.8899082568807339,
+      "grad_norm": 1.2812373865753657,
+      "learning_rate": 7.293615845160196e-07,
+      "loss": 0.9289,
+      "step": 970
+    },
+    {
+      "epoch": 0.8944954128440367,
+      "grad_norm": 1.2598363534447818,
+      "learning_rate": 6.705222963319191e-07,
+      "loss": 0.9375,
+      "step": 975
+    },
+    {
+      "epoch": 0.8990825688073395,
+      "grad_norm": 1.311487874418335,
+      "learning_rate": 6.140749454480932e-07,
+      "loss": 0.9116,
+      "step": 980
+    },
+    {
+      "epoch": 0.9036697247706422,
+      "grad_norm": 1.2877511107465471,
+      "learning_rate": 5.600340041135133e-07,
+      "loss": 0.9185,
+      "step": 985
+    },
+    {
+      "epoch": 0.908256880733945,
+      "grad_norm": 1.2931543960319436,
+      "learning_rate": 5.0841332761005e-07,
+      "loss": 0.9332,
+      "step": 990
+    },
+    {
+      "epoch": 0.9128440366972477,
+      "grad_norm": 1.180427274170459,
+      "learning_rate": 4.592261507001994e-07,
+      "loss": 0.9144,
+      "step": 995
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 1.2599014895347989,
+      "learning_rate": 4.124850842338779e-07,
+      "loss": 0.9195,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9220183486238532,
+      "grad_norm": 1.2650407345597277,
+      "learning_rate": 3.6820211191520127e-07,
+      "loss": 0.9233,
+      "step": 1005
+    },
+    {
+      "epoch": 0.926605504587156,
+      "grad_norm": 1.2740336020686558,
+      "learning_rate": 3.263885872300343e-07,
+      "loss": 0.9229,
+      "step": 1010
+    },
+    {
+      "epoch": 0.9311926605504587,
+      "grad_norm": 1.2585813421221876,
+      "learning_rate": 2.870552305351382e-07,
+      "loss": 0.9004,
+      "step": 1015
+    },
+    {
+      "epoch": 0.9357798165137615,
+      "grad_norm": 1.265046561795281,
+      "learning_rate": 2.5021212630962246e-07,
+      "loss": 0.9273,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9403669724770642,
+      "grad_norm": 1.2115732603108056,
+      "learning_rate": 2.158687205694443e-07,
+      "loss": 0.907,
+      "step": 1025
+    },
+    {
+      "epoch": 0.944954128440367,
+      "grad_norm": 1.2383709828148504,
+      "learning_rate": 1.840338184455881e-07,
+      "loss": 0.9273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9495412844036697,
+      "grad_norm": 1.2701853729566557,
+      "learning_rate": 1.5471558192656776e-07,
+      "loss": 0.9162,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9541284403669725,
+      "grad_norm": 1.2175490882454665,
+      "learning_rate": 1.279215277658097e-07,
+      "loss": 0.9324,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9587155963302753,
+      "grad_norm": 1.2654519384436929,
+      "learning_rate": 1.0365852555447642e-07,
+      "loss": 0.9251,
+      "step": 1045
+    },
+    {
+      "epoch": 0.963302752293578,
+      "grad_norm": 1.2262401130217693,
+      "learning_rate": 8.19327959602012e-08,
+      "loss": 0.9347,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9678899082568807,
+      "grad_norm": 1.252498856154254,
+      "learning_rate": 6.274990913221035e-08,
+      "loss": 0.9287,
+      "step": 1055
+    },
+    {
+      "epoch": 0.9724770642201835,
+      "grad_norm": 1.2498743795801759,
+      "learning_rate": 4.6114783273213395e-08,
+      "loss": 0.9137,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9770642201834863,
+      "grad_norm": 1.2653583861940565,
+      "learning_rate": 3.203168337845508e-08,
+      "loss": 0.9067,
+      "step": 1065
+    },
+    {
+      "epoch": 0.981651376146789,
+      "grad_norm": 1.2716276154907005,
+      "learning_rate": 2.05042201422323e-08,
+      "loss": 0.9157,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9862385321100917,
+      "grad_norm": 1.2922733325507376,
+      "learning_rate": 1.1535349032167908e-08,
+      "loss": 0.8985,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9908256880733946,
+      "grad_norm": 1.2484185326437052,
+      "learning_rate": 5.127369531473525e-09,
+      "loss": 0.9282,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9954128440366973,
+      "grad_norm": 1.2964676313466048,
+      "learning_rate": 1.2819245493955746e-09,
+      "loss": 0.9246,
+      "step": 1085
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.33366290382446,
+      "learning_rate": 0.0,
+      "loss": 0.9201,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9365631341934204,
+      "eval_runtime": 506.8306,
+      "eval_samples_per_second": 30.446,
+      "eval_steps_per_second": 0.477,
+      "step": 1090
+    },
+    {
+      "epoch": 1.0,
+      "step": 1090,
+      "total_flos": 456447649382400.0,
+      "train_loss": 0.9783915571116526,
+      "train_runtime": 14076.1137,
+      "train_samples_per_second": 9.905,
+      "train_steps_per_second": 0.077
+    }
+  ],
+  "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
+}