Model save

README.md

@@ -0,0 +1,64 @@
+---
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-marco13bv5-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-marco13bv5-sft-full
+
+This model was trained from scratch on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8860
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8826        | 1.0   | 1142 | 0.8860          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.8859861493110657,
+    "eval_runtime": 543.8003,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 29.728,
+    "eval_steps_per_second": 0.465,
+    "train_loss": 0.908709870119646,
+    "train_runtime": 20356.4656,
+    "train_samples": 207865,
+    "train_samples_per_second": 7.175,
+    "train_steps_per_second": 0.056
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.8859861493110657,
+    "eval_runtime": 543.8003,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 29.728,
+    "eval_steps_per_second": 0.465
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2",
+  "use_cache": false
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f69f805dc9d2e4693874da054202343b89408e75521cae086faffdd8c48b1a
+size 4978265800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5600dbcd4bed047e4efc53e584fd7d0e5ff09df5e37fbcd6e1b8733a485f9173
+size 4970422232

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe4fdc896d92539baa6cc2693a0de79d7757ad5d4ec12dbddceb0816cd75137
+size 4970422256

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61762c12091d1a726d705133aff6e97949a121bd87d69fa1dbb8d08c535c7ffe
+size 4933701504

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b758ba9eb40e1681e9adacc885cef1016ee50cbf5d9b10107ebedd4a78e0c5
+size 4933722216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609258cff9057d3f48d7b4c772bce98c9ebb8495b2002f9675e662d7b9539e7e
+size 1245236920

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

runs/Jan31_03-21-02_dsw-691-5496b4c68c-rxngp/events.out.tfevents.1706671346.dsw-691-5496b4c68c-rxngp.1401680.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92cd0fc1c1a93dc6b8191b2f648f018f247934ddb3e10aaa14305d9f97e8364b
-size 36084
+oid sha256:7dc2f3feaf9ac0deac9fddc32528404fc6c0ee5525b6c9a3989b181cbf92a5ca
+size 41105

runs/Jan31_03-21-02_dsw-691-5496b4c68c-rxngp/events.out.tfevents.1706692246.dsw-691-5496b4c68c-rxngp.1401680.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af99aa845fb86d821045437d86084b24c18845dd76f6316f80f7bc403e6f3d4e
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.908709870119646,
+    "train_runtime": 20356.4656,
+    "train_samples": 207865,
+    "train_samples_per_second": 7.175,
+    "train_steps_per_second": 0.056
+}

trainer_state.json

@@ -0,0 +1,1412 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1142,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.7391304347826088e-07,
+      "loss": 1.223,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.2044,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.2031,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.1387,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 1.1093,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 1.0924,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 1.072,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 1.0623,
+      "step": 35
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 1.0619,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 1.0515,
+      "step": 45
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 1.0545,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 1.0347,
+      "step": 55
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0434782608695653e-05,
+      "loss": 1.0527,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1304347826086957e-05,
+      "loss": 1.0333,
+      "step": 65
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2173913043478263e-05,
+      "loss": 1.038,
+      "step": 70
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.3043478260869566e-05,
+      "loss": 1.0071,
+      "step": 75
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.391304347826087e-05,
+      "loss": 0.9955,
+      "step": 80
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4782608695652174e-05,
+      "loss": 0.9602,
+      "step": 85
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.565217391304348e-05,
+      "loss": 0.9443,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.6521739130434785e-05,
+      "loss": 0.9319,
+      "step": 95
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.739130434782609e-05,
+      "loss": 0.9582,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.9322,
+      "step": 105
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9130434782608697e-05,
+      "loss": 0.929,
+      "step": 110
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 0.9348,
+      "step": 115
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9998830337935488e-05,
+      "loss": 0.917,
+      "step": 120
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9995321625363814e-05,
+      "loss": 0.9237,
+      "step": 125
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.998947468308658e-05,
+      "loss": 0.9136,
+      "step": 130
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9981290878893103e-05,
+      "loss": 0.9252,
+      "step": 135
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.997077212724044e-05,
+      "loss": 0.9378,
+      "step": 140
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9957920888805548e-05,
+      "loss": 0.9202,
+      "step": 145
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9942740169909643e-05,
+      "loss": 0.9264,
+      "step": 150
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9925233521814926e-05,
+      "loss": 0.9211,
+      "step": 155
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9905405039893827e-05,
+      "loss": 0.9173,
+      "step": 160
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9883259362670967e-05,
+      "loss": 0.9139,
+      "step": 165
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9858801670738052e-05,
+      "loss": 0.9228,
+      "step": 170
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9832037685541973e-05,
+      "loss": 0.9295,
+      "step": 175
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9802973668046364e-05,
+      "loss": 0.9144,
+      "step": 180
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9771616417266966e-05,
+      "loss": 0.9098,
+      "step": 185
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9737973268681117e-05,
+      "loss": 0.9196,
+      "step": 190
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.970205209251174e-05,
+      "loss": 0.9126,
+      "step": 195
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9663861291886256e-05,
+      "loss": 0.9306,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9623409800870804e-05,
+      "loss": 0.9232,
+      "step": 205
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.958070708238028e-05,
+      "loss": 0.9076,
+      "step": 210
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.953576312596466e-05,
+      "loss": 0.9342,
+      "step": 215
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9488588445472115e-05,
+      "loss": 0.9122,
+      "step": 220
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9439194076589477e-05,
+      "loss": 0.898,
+      "step": 225
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.938759157426065e-05,
+      "loss": 0.9153,
+      "step": 230
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9333793009983505e-05,
+      "loss": 0.9251,
+      "step": 235
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9277810968986004e-05,
+      "loss": 0.9008,
+      "step": 240
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.921965854728207e-05,
+      "loss": 0.9306,
+      "step": 245
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.915934934860803e-05,
+      "loss": 0.9088,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.909689748124025e-05,
+      "loss": 0.9164,
+      "step": 255
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9032317554694756e-05,
+      "loss": 0.9223,
+      "step": 260
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.896562467630959e-05,
+      "loss": 0.909,
+      "step": 265
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.889683444771071e-05,
+      "loss": 0.9043,
+      "step": 270
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8825962961162284e-05,
+      "loss": 0.9184,
+      "step": 275
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8753026795802158e-05,
+      "loss": 0.901,
+      "step": 280
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8678043013763493e-05,
+      "loss": 0.9279,
+      "step": 285
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.860102915618334e-05,
+      "loss": 0.8989,
+      "step": 290
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.852200323909924e-05,
+      "loss": 0.9171,
+      "step": 295
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8440983749234647e-05,
+      "loss": 0.9161,
+      "step": 300
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8357989639674324e-05,
+      "loss": 0.9168,
+      "step": 305
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8273040325430575e-05,
+      "loss": 0.8941,
+      "step": 310
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8186155678901457e-05,
+      "loss": 0.9092,
+      "step": 315
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8097356025221975e-05,
+      "loss": 0.908,
+      "step": 320
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.800666213750938e-05,
+      "loss": 0.9004,
+      "step": 325
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.791409523200366e-05,
+      "loss": 0.901,
+      "step": 330
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.781967696310437e-05,
+      "loss": 0.9391,
+      "step": 335
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.772342941830499e-05,
+      "loss": 0.9081,
+      "step": 340
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.76253751130259e-05,
+      "loss": 0.9115,
+      "step": 345
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7525536985347328e-05,
+      "loss": 0.9068,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.7423938390643384e-05,
+      "loss": 0.9072,
+      "step": 355
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.7320603096118476e-05,
+      "loss": 0.9124,
+      "step": 360
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.721555527524739e-05,
+      "loss": 0.9032,
+      "step": 365
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.710881950212033e-05,
+      "loss": 0.9045,
+      "step": 370
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.7000420745694256e-05,
+      "loss": 0.8997,
+      "step": 375
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.6890384363951802e-05,
+      "loss": 0.9109,
+      "step": 380
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.6778736097969258e-05,
+      "loss": 0.8979,
+      "step": 385
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.666550206589489e-05,
+      "loss": 0.8957,
+      "step": 390
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.655070875683904e-05,
+      "loss": 0.8963,
+      "step": 395
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6434383024677475e-05,
+      "loss": 0.9028,
+      "step": 400
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.6316552081769404e-05,
+      "loss": 0.9216,
+      "step": 405
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6197243492591627e-05,
+      "loss": 0.9171,
+      "step": 410
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6076485167290278e-05,
+      "loss": 0.9059,
+      "step": 415
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.5954305355151775e-05,
+      "loss": 0.9053,
+      "step": 420
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.5830732637994382e-05,
+      "loss": 0.9027,
+      "step": 425
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5705795923481995e-05,
+      "loss": 0.9068,
+      "step": 430
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.5579524438361693e-05,
+      "loss": 0.8966,
+      "step": 435
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5451947721626676e-05,
+      "loss": 0.9028,
+      "step": 440
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.532309561760612e-05,
+      "loss": 0.8978,
+      "step": 445
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.5192998268983625e-05,
+      "loss": 0.9181,
+      "step": 450
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.506168610974587e-05,
+      "loss": 0.8942,
+      "step": 455
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.4929189858063103e-05,
+      "loss": 0.8978,
+      "step": 460
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4795540509103182e-05,
+      "loss": 0.9068,
+      "step": 465
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.4660769327780796e-05,
+      "loss": 0.9053,
+      "step": 470
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4524907841443576e-05,
+      "loss": 0.9018,
+      "step": 475
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4387987832496848e-05,
+      "loss": 0.9095,
+      "step": 480
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.4250041330968674e-05,
+      "loss": 0.8824,
+      "step": 485
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.411110060701701e-05,
+      "loss": 0.905,
+      "step": 490
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.3971198163380659e-05,
+      "loss": 0.8961,
+      "step": 495
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.3830366727775835e-05,
+      "loss": 0.8865,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.3688639245240078e-05,
+      "loss": 0.8926,
+      "step": 505
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3546048870425356e-05,
+      "loss": 0.9027,
+      "step": 510
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.3402628959842106e-05,
+      "loss": 0.9049,
+      "step": 515
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.3258413064056066e-05,
+      "loss": 0.8778,
+      "step": 520
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.3113434919839715e-05,
+      "loss": 0.8943,
+      "step": 525
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.2967728442280154e-05,
+      "loss": 0.8858,
+      "step": 530
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2821327716845246e-05,
+      "loss": 0.8833,
+      "step": 535
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.2674266991409949e-05,
+      "loss": 0.8963,
+      "step": 540
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2526580668244607e-05,
+      "loss": 0.8908,
+      "step": 545
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.2378303295967147e-05,
+      "loss": 0.8985,
+      "step": 550
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2229469561461046e-05,
+      "loss": 0.9021,
+      "step": 555
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.2080114281760942e-05,
+      "loss": 0.9056,
+      "step": 560
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.1930272395907789e-05,
+      "loss": 0.898,
+      "step": 565
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.1779978956775507e-05,
+      "loss": 0.8985,
+      "step": 570
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.1629269122870942e-05,
+      "loss": 0.9042,
+      "step": 575
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.14781781501092e-05,
+      "loss": 0.8845,
+      "step": 580
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.1326741383566102e-05,
+      "loss": 0.8977,
+      "step": 585
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.1174994249209852e-05,
+      "loss": 0.8871,
+      "step": 590
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.1022972245613735e-05,
+      "loss": 0.9106,
+      "step": 595
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.0870710935651868e-05,
+      "loss": 0.903,
+      "step": 600
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.0718245938179886e-05,
+      "loss": 0.8802,
+      "step": 605
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.0565612919702527e-05,
+      "loss": 0.8879,
+      "step": 610
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.041284758603009e-05,
+      "loss": 0.9077,
+      "step": 615
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.0259985673925694e-05,
+      "loss": 0.8867,
+      "step": 620
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.0107062942745276e-05,
+      "loss": 0.8868,
+      "step": 625
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.95411516607233e-06,
+      "loss": 0.888,
+      "step": 630
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.801178123349298e-06,
+      "loss": 0.9066,
+      "step": 635
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.648287591507613e-06,
+      "loss": 0.8995,
+      "step": 640
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.49547933659829e-06,
+      "loss": 0.8952,
+      "step": 645
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.34278910542512e-06,
+      "loss": 0.888,
+      "step": 650
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.190252617182301e-06,
+      "loss": 0.8911,
+      "step": 655
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.037905555098589e-06,
+      "loss": 0.8934,
+      "step": 660
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.88578355808981e-06,
+      "loss": 0.8905,
+      "step": 665
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.733922212421785e-06,
+      "loss": 0.8763,
+      "step": 670
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.582357043385529e-06,
+      "loss": 0.8957,
+      "step": 675
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.431123506986747e-06,
+      "loss": 0.9015,
+      "step": 680
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.280256981651527e-06,
+      "loss": 0.886,
+      "step": 685
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.129792759950157e-06,
+      "loss": 0.8913,
+      "step": 690
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.979766040341084e-06,
+      "loss": 0.884,
+      "step": 695
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.83021191893682e-06,
+      "loss": 0.8935,
+      "step": 700
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.68116538129385e-06,
+      "loss": 0.8903,
+      "step": 705
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.53266129422835e-06,
+      "loss": 0.8685,
+      "step": 710
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.3847343976597454e-06,
+      "loss": 0.8763,
+      "step": 715
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.237419296483876e-06,
+      "loss": 0.9013,
+      "step": 720
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.09075045247782e-06,
+      "loss": 0.8755,
+      "step": 725
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.944762176238149e-06,
+      "loss": 0.9027,
+      "step": 730
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.799488619154586e-06,
+      "loss": 0.8952,
+      "step": 735
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.654963765420866e-06,
+      "loss": 0.879,
+      "step": 740
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.511221424084748e-06,
+      "loss": 0.8966,
+      "step": 745
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.3682952211389735e-06,
+      "loss": 0.8885,
+      "step": 750
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.226218591655071e-06,
+      "loss": 0.8966,
+      "step": 755
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 6.085024771961792e-06,
+      "loss": 0.8881,
+      "step": 760
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.944746791870062e-06,
+      "loss": 0.8742,
+      "step": 765
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.8054174669462425e-06,
+      "loss": 0.873,
+      "step": 770
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.667069390835496e-06,
+      "loss": 0.8789,
+      "step": 775
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.529734927637096e-06,
+      "loss": 0.8773,
+      "step": 780
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.393446204333386e-06,
+      "loss": 0.8865,
+      "step": 785
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.258235103274265e-06,
+      "loss": 0.8666,
+      "step": 790
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.1241332547188535e-06,
+      "loss": 0.894,
+      "step": 795
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.991172029436157e-06,
+      "loss": 0.8827,
+      "step": 800
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.859382531366428e-06,
+      "loss": 0.8687,
+      "step": 805
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.728795590344948e-06,
+      "loss": 0.8737,
+      "step": 810
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.599441754889919e-06,
+      "loss": 0.8704,
+      "step": 815
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.471351285056192e-06,
+      "loss": 0.8602,
+      "step": 820
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.344554145356447e-06,
+      "loss": 0.8815,
+      "step": 825
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.219079997751515e-06,
+      "loss": 0.8788,
+      "step": 830
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.0949581947115106e-06,
+      "loss": 0.8932,
+      "step": 835
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.972217772349309e-06,
+      "loss": 0.8818,
+      "step": 840
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.850887443628075e-06,
+      "loss": 0.8914,
+      "step": 845
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.7309955916443597e-06,
+      "loss": 0.8758,
+      "step": 850
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.612570262988393e-06,
+      "loss": 0.8869,
+      "step": 855
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.4956391611830486e-06,
+      "loss": 0.8841,
+      "step": 860
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.3802296402031234e-06,
+      "loss": 0.896,
+      "step": 865
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.266368698076323e-06,
+      "loss": 0.8891,
+      "step": 870
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.1540829705675835e-06,
+      "loss": 0.8743,
+      "step": 875
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.043398724948068e-06,
+      "loss": 0.8846,
+      "step": 880
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.9343418538504297e-06,
+      "loss": 0.8715,
+      "step": 885
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.8269378692116676e-06,
+      "loss": 0.8753,
+      "step": 890
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.721211896305059e-06,
+      "loss": 0.8814,
+      "step": 895
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.6171886678625593e-06,
+      "loss": 0.8792,
+      "step": 900
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.514892518288988e-06,
+      "loss": 0.8838,
+      "step": 905
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.4143473779694548e-06,
+      "loss": 0.885,
+      "step": 910
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.3155767676712317e-06,
+      "loss": 0.8936,
+      "step": 915
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.218603793041516e-06,
+      "loss": 0.8704,
+      "step": 920
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.1234511392022473e-06,
+      "loss": 0.8797,
+      "step": 925
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.0301410654433307e-06,
+      "loss": 0.8728,
+      "step": 930
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.938695400015467e-06,
+      "loss": 0.8907,
+      "step": 935
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.849135535023825e-06,
+      "loss": 0.8855,
+      "step": 940
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7614824214237158e-06,
+      "loss": 0.8857,
+      "step": 945
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6757565641195073e-06,
+      "loss": 0.8916,
+      "step": 950
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.5919780171678412e-06,
+      "loss": 0.8912,
+      "step": 955
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.5101663790863597e-06,
+      "loss": 0.8789,
+      "step": 960
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4303407882689635e-06,
+      "loss": 0.871,
+      "step": 965
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3525199185087223e-06,
+      "loss": 0.8827,
+      "step": 970
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2767219746294724e-06,
+      "loss": 0.8904,
+      "step": 975
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2029646882271173e-06,
+      "loss": 0.8848,
+      "step": 980
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.131265313521639e-06,
+      "loss": 0.8738,
+      "step": 985
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.06164062332076e-06,
+      "loss": 0.8779,
+      "step": 990
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.941069050962626e-07,
+      "loss": 0.8871,
+      "step": 995
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.286799571737981e-07,
+      "loss": 0.8733,
+      "step": 1000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.653750850371667e-07,
+      "loss": 0.8712,
+      "step": 1005
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.042070977478533e-07,
+      "loss": 0.8785,
+      "step": 1010
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.451903044807185e-07,
+      "loss": 0.8748,
+      "step": 1015
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.883385111766139e-07,
+      "loss": 0.8682,
+      "step": 1020
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.336650173127224e-07,
+      "loss": 0.884,
+      "step": 1025
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.811826127913855e-07,
+      "loss": 0.8665,
+      "step": 1030
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.309035749481295e-07,
+      "loss": 0.8758,
+      "step": 1035
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.828396656795964e-07,
+      "loss": 0.8835,
+      "step": 1040
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.3700212869205117e-07,
+      "loss": 0.8861,
+      "step": 1045
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.934016868711266e-07,
+      "loss": 0.8762,
+      "step": 1050
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.520485397733786e-07,
+      "loss": 0.8697,
+      "step": 1055
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.129523612402918e-07,
+      "loss": 0.9092,
+      "step": 1060
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.761222971352451e-07,
+      "loss": 0.8828,
+      "step": 1065
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.4156696320399963e-07,
+      "loss": 0.8741,
+      "step": 1070
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0929444305920142e-07,
+      "loss": 0.8691,
+      "step": 1075
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.7931228628935926e-07,
+      "loss": 0.8818,
+      "step": 1080
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5162750669274973e-07,
+      "loss": 0.8684,
+      "step": 1085
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.262465806366664e-07,
+      "loss": 0.8709,
+      "step": 1090
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.0317544554238058e-07,
+      "loss": 0.8805,
+      "step": 1095
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.241949849619457e-08,
+      "loss": 0.8923,
+      "step": 1100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 6.398359498688278e-08,
+      "loss": 0.8889,
+      "step": 1105
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.787204776983689e-08,
+      "loss": 0.8644,
+      "step": 1110
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.4088625858174075e-08,
+      "loss": 0.8637,
+      "step": 1115
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.2636553641040003e-08,
+      "loss": 0.8687,
+      "step": 1120
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.351851012931893e-08,
+      "loss": 0.8688,
+      "step": 1125
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.736628328933847e-09,
+      "loss": 0.8801,
+      "step": 1130
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.2924947418556666e-09,
+      "loss": 0.8763,
+      "step": 1135
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.8714899497895845e-10,
+      "loss": 0.8826,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8859861493110657,
+      "eval_runtime": 543.8854,
+      "eval_samples_per_second": 29.723,
+      "eval_steps_per_second": 0.465,
+      "step": 1142
+    },
+    {
+      "epoch": 1.0,
+      "step": 1142,
+      "total_flos": 2.3084944059126514e+19,
+      "train_loss": 0.908709870119646,
+      "train_runtime": 20356.4656,
+      "train_samples_per_second": 7.175,
+      "train_steps_per_second": 0.056
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1142,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 2.3084944059126514e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}