Model save

README.md

@@ -0,0 +1,70 @@
+---
+license: mit
+base_model: microsoft/Phi-3-small-8k-instruct
+tags:
+- generated_from_trainer
+model-index:
+- name: phi3-spin-zephyr-data
+  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. -->
+
+# phi3-spin-zephyr-data
+
+This model is a fine-tuned version of [microsoft/Phi-3-small-8k-instruct](https://huggingface.co/microsoft/Phi-3-small-8k-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1680
+- Rewards/real: -6.9251
+- Rewards/generated: -22.7311
+- Rewards/accuracies: 0.9443
+- Rewards/margins: 15.8060
+- Logps/generated: -518.7460
+- Logps/real: -321.6379
+- Logits/generated: -inf
+- Logits/real: -inf
+
+## 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: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
+| 0.2807        | 0.64  | 500  | 0.1680          | -6.9251      | -22.7311          | 0.9443             | 15.8060         | -518.7460       | -321.6379  | -inf             | -inf        |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6284302195911938,
+    "train_runtime": 5860.6637,
+    "train_samples": 25000,
+    "train_samples_per_second": 4.266,
+    "train_steps_per_second": 0.133
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": [
+    100257,
+    100266
+  ],
+  "transformers_version": "4.37.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61a098b9291287a13df8ae4fcdb00643a5ec324bf65af655801e5cb47a21618
+size 4832943104

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b112110dccae5c1237da32a3ef6bd78b31a00f092836ea5d6725a775764041d
+size 4799608224

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8607487f2f6919b39039edda7f2d6f3a681042b5433ed53b46c2b0e1484738
+size 4799608240

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713883d1a11f48447b2142edf25e4ea6b77b0ed0851ce9d404c3ca3b854a8975
+size 352437304

model.safetensors.index.json

@@ -0,0 +1,426 @@
+{
+  "metadata": {
+    "total_size": 14784548864
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.final_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.final_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.dense.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.dense.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.dense.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.dense.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.dense.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.dense.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00004.safetensors"
+  }
+}

runs/Jul24_05-07-12_gilbreth-j001.rcac.purdue.edu/events.out.tfevents.1721812169.gilbreth-j001.rcac.purdue.edu.196523.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab9f0d4b2e917f9558bbcf7b8a8a4d37de43d350c736f1c53e87a737e5f488a
-size 52207
+oid sha256:21230c114f40c9ed1a1355ab812c108245c87792e72f99e9038461341b167e29
+size 57609

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6284302195911938,
+    "train_runtime": 5860.6637,
+    "train_samples": 25000,
+    "train_samples_per_second": 4.266,
+    "train_steps_per_second": 0.133
+}

trainer_state.json

@@ -0,0 +1,1152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 782,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.329113924050633e-09,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -403.3199157714844,
+      "logps/real": -443.6107177734375,
+      "loss": 4.7453,
+      "rewards/accuracies": 0.5,
+      "rewards/generated": -12.943833351135254,
+      "rewards/margins": -2.53641414642334,
+      "rewards/real": -15.48024845123291,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.329113924050633e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -487.2403869628906,
+      "logps/real": -384.84637451171875,
+      "loss": 3.4512,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/generated": -19.510425567626953,
+      "rewards/margins": 6.074762344360352,
+      "rewards/real": -13.435664176940918,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.2658227848101266e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -473.37353515625,
+      "logps/real": -413.13916015625,
+      "loss": 3.9704,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/generated": -18.36065101623535,
+      "rewards/margins": 3.8984241485595703,
+      "rewards/real": -14.462226867675781,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.89873417721519e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -510.23455810546875,
+      "logps/real": -408.78350830078125,
+      "loss": 3.6848,
+      "rewards/accuracies": 0.6875,
+      "rewards/generated": -21.037378311157227,
+      "rewards/margins": 7.7357025146484375,
+      "rewards/real": -13.301675796508789,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.5316455696202533e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -451.669189453125,
+      "logps/real": -368.1625061035156,
+      "loss": 3.9079,
+      "rewards/accuracies": 0.625,
+      "rewards/generated": -16.798627853393555,
+      "rewards/margins": 4.454809665679932,
+      "rewards/real": -12.343819618225098,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.1645569620253163e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -552.6080322265625,
+      "logps/real": -397.91064453125,
+      "loss": 2.9787,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/generated": -25.66506004333496,
+      "rewards/margins": 10.62718391418457,
+      "rewards/real": -15.037874221801758,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.79746835443038e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -509.36578369140625,
+      "logps/real": -390.8323059082031,
+      "loss": 2.5737,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/generated": -22.55277442932129,
+      "rewards/margins": 7.870760440826416,
+      "rewards/real": -14.682014465332031,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.4303797468354424e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -554.7327270507812,
+      "logps/real": -382.78350830078125,
+      "loss": 1.7978,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/generated": -28.232168197631836,
+      "rewards/margins": 14.969076156616211,
+      "rewards/real": -13.263090133666992,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.992887624466572e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -573.7469482421875,
+      "logps/real": -402.5927429199219,
+      "loss": 1.4178,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/generated": -28.089534759521484,
+      "rewards/margins": 12.5045166015625,
+      "rewards/real": -15.5850191116333,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.92176386913229e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -576.7484741210938,
+      "logps/real": -400.97186279296875,
+      "loss": 1.2467,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/generated": -30.259912490844727,
+      "rewards/margins": 14.735580444335938,
+      "rewards/real": -15.524327278137207,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.850640113798008e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -654.0052490234375,
+      "logps/real": -442.6397399902344,
+      "loss": 0.9329,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": -35.535160064697266,
+      "rewards/margins": 18.725465774536133,
+      "rewards/real": -16.8096923828125,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.779516358463727e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -638.0022583007812,
+      "logps/real": -427.4214782714844,
+      "loss": 1.1736,
+      "rewards/accuracies": 0.875,
+      "rewards/generated": -35.03214645385742,
+      "rewards/margins": 18.788606643676758,
+      "rewards/real": -16.24354362487793,
+      "step": 110
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.7083926031294454e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -647.80859375,
+      "logps/real": -420.6051330566406,
+      "loss": 0.7488,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -35.87686538696289,
+      "rewards/margins": 21.418781280517578,
+      "rewards/real": -14.458081245422363,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6372688477951633e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -647.1038818359375,
+      "logps/real": -412.8779296875,
+      "loss": 0.6447,
+      "rewards/accuracies": 0.875,
+      "rewards/generated": -35.35771560668945,
+      "rewards/margins": 20.0076904296875,
+      "rewards/real": -15.350027084350586,
+      "step": 130
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.5661450924608817e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -699.005126953125,
+      "logps/real": -401.8106384277344,
+      "loss": 0.9455,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -38.48512268066406,
+      "rewards/margins": 23.671005249023438,
+      "rewards/real": -14.814119338989258,
+      "step": 140
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.4950213371266e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -673.933349609375,
+      "logps/real": -404.8531494140625,
+      "loss": 0.6848,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/generated": -38.79594039916992,
+      "rewards/margins": 22.858118057250977,
+      "rewards/real": -15.937822341918945,
+      "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.4238975817923186e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -650.0132446289062,
+      "logps/real": -380.55413818359375,
+      "loss": 0.5912,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": -36.62251663208008,
+      "rewards/margins": 22.439044952392578,
+      "rewards/real": -14.183469772338867,
+      "step": 160
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.3527738264580364e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -676.5908203125,
+      "logps/real": -413.38287353515625,
+      "loss": 0.6238,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/generated": -37.932899475097656,
+      "rewards/margins": 22.803815841674805,
+      "rewards/real": -15.129079818725586,
+      "step": 170
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.2816500711237554e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -660.9660034179688,
+      "logps/real": -372.2694396972656,
+      "loss": 0.3412,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -37.31585693359375,
+      "rewards/margins": 23.456205368041992,
+      "rewards/real": -13.859651565551758,
+      "step": 180
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.2105263157894733e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -668.5888671875,
+      "logps/real": -366.01507568359375,
+      "loss": 0.5799,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -37.69170379638672,
+      "rewards/margins": 25.54647445678711,
+      "rewards/real": -12.145231246948242,
+      "step": 190
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.1394025604551917e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -681.8294677734375,
+      "logps/real": -392.57513427734375,
+      "loss": 0.6742,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": -38.56768035888672,
+      "rewards/margins": 24.48987579345703,
+      "rewards/real": -14.077804565429688,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.06827880512091e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -754.3670654296875,
+      "logps/real": -383.51702880859375,
+      "loss": 0.519,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -44.508426666259766,
+      "rewards/margins": 30.150854110717773,
+      "rewards/real": -14.357576370239258,
+      "step": 210
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.9971550497866285e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -669.1099243164062,
+      "logps/real": -404.3431091308594,
+      "loss": 0.3679,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -39.06100845336914,
+      "rewards/margins": 24.223697662353516,
+      "rewards/real": -14.837308883666992,
+      "step": 220
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.926031294452347e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -688.25048828125,
+      "logps/real": -396.00018310546875,
+      "loss": 0.2677,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -39.11343765258789,
+      "rewards/margins": 24.355987548828125,
+      "rewards/real": -14.757448196411133,
+      "step": 230
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.8549075391180653e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -714.4971923828125,
+      "logps/real": -415.25262451171875,
+      "loss": 0.4572,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -40.9525032043457,
+      "rewards/margins": 25.465791702270508,
+      "rewards/real": -15.486714363098145,
+      "step": 240
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.783783783783784e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -729.0126342773438,
+      "logps/real": -394.86724853515625,
+      "loss": 0.345,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -44.133033752441406,
+      "rewards/margins": 29.94510841369629,
+      "rewards/real": -14.187917709350586,
+      "step": 250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.7126600284495016e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -722.02490234375,
+      "logps/real": -403.8961181640625,
+      "loss": 0.4853,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -41.30921173095703,
+      "rewards/margins": 26.302785873413086,
+      "rewards/real": -15.006426811218262,
+      "step": 260
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.6415362731152206e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -695.8910522460938,
+      "logps/real": -374.00433349609375,
+      "loss": 0.3413,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -41.190391540527344,
+      "rewards/margins": 27.258630752563477,
+      "rewards/real": -13.931764602661133,
+      "step": 270
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.5704125177809385e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -734.4241943359375,
+      "logps/real": -404.4153137207031,
+      "loss": 0.4178,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -43.61100387573242,
+      "rewards/margins": 28.391124725341797,
+      "rewards/real": -15.219881057739258,
+      "step": 280
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.4992887624466574e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -703.3042602539062,
+      "logps/real": -400.789306640625,
+      "loss": 0.358,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -40.19432830810547,
+      "rewards/margins": 25.275157928466797,
+      "rewards/real": -14.919171333312988,
+      "step": 290
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.4281650071123753e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -717.597900390625,
+      "logps/real": -387.6546325683594,
+      "loss": 0.2285,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -42.98313522338867,
+      "rewards/margins": 27.72798728942871,
+      "rewards/real": -15.255144119262695,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.3570412517780937e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -714.7513427734375,
+      "logps/real": -424.5567932128906,
+      "loss": 0.362,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/generated": -42.02880859375,
+      "rewards/margins": 26.301555633544922,
+      "rewards/real": -15.727252006530762,
+      "step": 310
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.285917496443812e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -704.7682495117188,
+      "logps/real": -389.437744140625,
+      "loss": 0.3054,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -40.38294982910156,
+      "rewards/margins": 26.326675415039062,
+      "rewards/real": -14.05627727508545,
+      "step": 320
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.2147937411095305e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -788.1136474609375,
+      "logps/real": -426.383544921875,
+      "loss": 0.2255,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -49.49579620361328,
+      "rewards/margins": 32.605934143066406,
+      "rewards/real": -16.889863967895508,
+      "step": 330
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.1436699857752484e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -720.3298950195312,
+      "logps/real": -392.3839111328125,
+      "loss": 0.3118,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -42.088287353515625,
+      "rewards/margins": 27.807758331298828,
+      "rewards/real": -14.28053092956543,
+      "step": 340
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.0725462304409674e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -721.5670776367188,
+      "logps/real": -399.3511047363281,
+      "loss": 0.2108,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -44.001930236816406,
+      "rewards/margins": 28.8182430267334,
+      "rewards/real": -15.183688163757324,
+      "step": 350
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.001422475106685e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -734.0841064453125,
+      "logps/real": -473.2635192871094,
+      "loss": 0.6012,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -44.092620849609375,
+      "rewards/margins": 25.192630767822266,
+      "rewards/real": -18.89999008178711,
+      "step": 360
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.9302987197724037e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -666.3681030273438,
+      "logps/real": -369.57232666015625,
+      "loss": 0.3811,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -38.6079216003418,
+      "rewards/margins": 23.917612075805664,
+      "rewards/real": -14.690305709838867,
+      "step": 370
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.8591749644381226e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -709.2445068359375,
+      "logps/real": -394.5869140625,
+      "loss": 0.3208,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -42.30268096923828,
+      "rewards/margins": 26.500690460205078,
+      "rewards/real": -15.80199146270752,
+      "step": 380
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.7880512091038405e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -775.5260009765625,
+      "logps/real": -426.09869384765625,
+      "loss": 0.2884,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -48.343849182128906,
+      "rewards/margins": 31.10616683959961,
+      "rewards/real": -17.237682342529297,
+      "step": 390
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.716927453769559e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -773.4555053710938,
+      "logps/real": -450.7288513183594,
+      "loss": 0.3376,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -47.49498748779297,
+      "rewards/margins": 28.620986938476562,
+      "rewards/real": -18.873998641967773,
+      "step": 400
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.6458036984352773e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -741.7351684570312,
+      "logps/real": -449.17816162109375,
+      "loss": 0.3754,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -46.99356460571289,
+      "rewards/margins": 27.995086669921875,
+      "rewards/real": -18.998476028442383,
+      "step": 410
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.574679943100996e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -738.3614501953125,
+      "logps/real": -456.7314453125,
+      "loss": 0.0844,
+      "rewards/accuracies": 0.9375,
+      "rewards/generated": -46.36874008178711,
+      "rewards/margins": 27.84047508239746,
+      "rewards/real": -18.528268814086914,
+      "step": 420
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.5035561877667136e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -768.1492309570312,
+      "logps/real": -441.343017578125,
+      "loss": 0.1898,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -47.066619873046875,
+      "rewards/margins": 29.435678482055664,
+      "rewards/real": -17.63094139099121,
+      "step": 430
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.4324324324324326e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -787.4987182617188,
+      "logps/real": -408.2841796875,
+      "loss": 0.3922,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -50.27423095703125,
+      "rewards/margins": 33.921939849853516,
+      "rewards/real": -16.352293014526367,
+      "step": 440
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.3613086770981507e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -771.3111572265625,
+      "logps/real": -408.37896728515625,
+      "loss": 0.3608,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -48.568450927734375,
+      "rewards/margins": 31.147785186767578,
+      "rewards/real": -17.420665740966797,
+      "step": 450
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.290184921763869e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -827.6937255859375,
+      "logps/real": -423.6630859375,
+      "loss": 0.1253,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -51.94307327270508,
+      "rewards/margins": 35.77669143676758,
+      "rewards/real": -16.166385650634766,
+      "step": 460
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.2190611664295875e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -790.8399658203125,
+      "logps/real": -440.3358459472656,
+      "loss": 0.2949,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -48.574867248535156,
+      "rewards/margins": 30.353759765625,
+      "rewards/real": -18.22110939025879,
+      "step": 470
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.1479374110953057e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -781.35791015625,
+      "logps/real": -390.54168701171875,
+      "loss": 0.3877,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -49.05020523071289,
+      "rewards/margins": 32.30176544189453,
+      "rewards/real": -16.748441696166992,
+      "step": 480
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.076813655761024e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -810.448486328125,
+      "logps/real": -441.8717346191406,
+      "loss": 0.2217,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -51.156005859375,
+      "rewards/margins": 31.813852310180664,
+      "rewards/real": -19.342153549194336,
+      "step": 490
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.0056899004267425e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -802.3043212890625,
+      "logps/real": -487.0044860839844,
+      "loss": 0.2807,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -51.0858039855957,
+      "rewards/margins": 30.591796875,
+      "rewards/real": -20.494003295898438,
+      "step": 500
+    },
+    {
+      "epoch": 0.64,
+      "eval_logits/generated": -Infinity,
+      "eval_logits/real": -Infinity,
+      "eval_logps/generated": -518.7460327148438,
+      "eval_logps/real": -321.637939453125,
+      "eval_loss": 0.16799330711364746,
+      "eval_rewards/accuracies": 0.9442675113677979,
+      "eval_rewards/generated": -22.73108673095703,
+      "eval_rewards/margins": 15.805987358093262,
+      "eval_rewards/real": -6.9250993728637695,
+      "eval_runtime": 514.9684,
+      "eval_samples_per_second": 9.709,
+      "eval_steps_per_second": 0.305,
+      "step": 500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.9345661450924607e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -764.2227783203125,
+      "logps/real": -417.8741149902344,
+      "loss": 0.2566,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -46.21670150756836,
+      "rewards/margins": 29.2624568939209,
+      "rewards/real": -16.954248428344727,
+      "step": 510
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.863442389758179e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -785.6708984375,
+      "logps/real": -436.8841857910156,
+      "loss": 0.2175,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -50.03806686401367,
+      "rewards/margins": 33.52396011352539,
+      "rewards/real": -16.514102935791016,
+      "step": 520
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7923186344238975e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -741.9736328125,
+      "logps/real": -408.57763671875,
+      "loss": 0.3024,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -45.586387634277344,
+      "rewards/margins": 29.933719635009766,
+      "rewards/real": -15.652669906616211,
+      "step": 530
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.721194879089616e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -813.8468017578125,
+      "logps/real": -430.96026611328125,
+      "loss": 0.2112,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -52.11174392700195,
+      "rewards/margins": 33.244110107421875,
+      "rewards/real": -18.867637634277344,
+      "step": 540
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.650071123755334e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -813.7432250976562,
+      "logps/real": -425.29754638671875,
+      "loss": 0.3095,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -52.5365104675293,
+      "rewards/margins": 34.71119689941406,
+      "rewards/real": -17.825315475463867,
+      "step": 550
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.5789473684210525e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -790.2058715820312,
+      "logps/real": -440.711669921875,
+      "loss": 0.1864,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -49.65260314941406,
+      "rewards/margins": 31.609088897705078,
+      "rewards/real": -18.04351234436035,
+      "step": 560
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.507823613086771e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -752.94677734375,
+      "logps/real": -427.7891540527344,
+      "loss": 0.3443,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -47.858802795410156,
+      "rewards/margins": 30.949520111083984,
+      "rewards/real": -16.90927505493164,
+      "step": 570
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.436699857752489e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -843.44140625,
+      "logps/real": -425.5953063964844,
+      "loss": 0.3088,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -53.65172576904297,
+      "rewards/margins": 36.3214111328125,
+      "rewards/real": -17.330326080322266,
+      "step": 580
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.3655761024182077e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -816.5244750976562,
+      "logps/real": -419.6240234375,
+      "loss": 0.2445,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -52.9045524597168,
+      "rewards/margins": 36.242149353027344,
+      "rewards/real": -16.662403106689453,
+      "step": 590
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.2944523470839261e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -824.7449340820312,
+      "logps/real": -429.56414794921875,
+      "loss": 0.3351,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -51.94647979736328,
+      "rewards/margins": 34.617332458496094,
+      "rewards/real": -17.329151153564453,
+      "step": 600
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.2233285917496443e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -775.5467529296875,
+      "logps/real": -422.3451232910156,
+      "loss": 0.07,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -48.54518508911133,
+      "rewards/margins": 32.839900970458984,
+      "rewards/real": -15.705281257629395,
+      "step": 610
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.1522048364153626e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -779.6900634765625,
+      "logps/real": -441.49365234375,
+      "loss": 0.2883,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -49.64753341674805,
+      "rewards/margins": 32.548099517822266,
+      "rewards/real": -17.099435806274414,
+      "step": 620
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.0810810810810811e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -785.1602172851562,
+      "logps/real": -403.9580993652344,
+      "loss": 0.1209,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -49.906761169433594,
+      "rewards/margins": 33.77416229248047,
+      "rewards/real": -16.13260269165039,
+      "step": 630
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0099573257467994e-07,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -830.7962036132812,
+      "logps/real": -457.5830993652344,
+      "loss": 0.2802,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -53.04398727416992,
+      "rewards/margins": 34.22355270385742,
+      "rewards/real": -18.820430755615234,
+      "step": 640
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.388335704125178e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -774.2494506835938,
+      "logps/real": -407.559326171875,
+      "loss": 0.1348,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -49.61153030395508,
+      "rewards/margins": 32.225975036621094,
+      "rewards/real": -17.385555267333984,
+      "step": 650
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.677098150782361e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -772.5739135742188,
+      "logps/real": -409.3276672363281,
+      "loss": 0.0997,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -48.17709732055664,
+      "rewards/margins": 32.27601623535156,
+      "rewards/real": -15.901082038879395,
+      "step": 660
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.965860597439544e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -764.9151000976562,
+      "logps/real": -425.33709716796875,
+      "loss": 0.2364,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -48.48712921142578,
+      "rewards/margins": 31.54388427734375,
+      "rewards/real": -16.9432430267334,
+      "step": 670
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.254623044096728e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -822.6394653320312,
+      "logps/real": -434.67877197265625,
+      "loss": 0.242,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -53.5615348815918,
+      "rewards/margins": 35.22587585449219,
+      "rewards/real": -18.33565902709961,
+      "step": 680
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.543385490753911e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -868.9513549804688,
+      "logps/real": -439.777587890625,
+      "loss": 0.203,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -56.48514938354492,
+      "rewards/margins": 37.33259201049805,
+      "rewards/real": -19.152555465698242,
+      "step": 690
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.832147937411095e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -784.9397583007812,
+      "logps/real": -413.0848083496094,
+      "loss": 0.2787,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/generated": -47.916893005371094,
+      "rewards/margins": 29.88480567932129,
+      "rewards/real": -18.032087326049805,
+      "step": 700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.120910384068278e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -824.5567626953125,
+      "logps/real": -448.226318359375,
+      "loss": 0.2584,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/generated": -53.5278205871582,
+      "rewards/margins": 35.21510696411133,
+      "rewards/real": -18.312713623046875,
+      "step": 710
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.4096728307254624e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -828.8753662109375,
+      "logps/real": -427.9056091308594,
+      "loss": 0.1088,
+      "rewards/accuracies": 0.987500011920929,
+      "rewards/generated": -53.2839469909668,
+      "rewards/margins": 35.713260650634766,
+      "rewards/real": -17.57068634033203,
+      "step": 720
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.698435277382646e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -839.0155029296875,
+      "logps/real": -435.33428955078125,
+      "loss": 0.2107,
+      "rewards/accuracies": 1.0,
+      "rewards/generated": -55.168609619140625,
+      "rewards/margins": 37.164310455322266,
+      "rewards/real": -18.004301071166992,
+      "step": 730
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.9871977240398294e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -805.4227905273438,
+      "logps/real": -428.77923583984375,
+      "loss": 0.2453,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/generated": -52.77501678466797,
+      "rewards/margins": 34.709877014160156,
+      "rewards/real": -18.065141677856445,
+      "step": 740
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.275960170697013e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -834.6575927734375,
+      "logps/real": -415.8843688964844,
+      "loss": 0.1762,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -52.49644088745117,
+      "rewards/margins": 36.04848098754883,
+      "rewards/real": -16.447967529296875,
+      "step": 750
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.564722617354196e-08,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -850.2274169921875,
+      "logps/real": -395.8170471191406,
+      "loss": 0.1395,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -55.13444900512695,
+      "rewards/margins": 38.56990432739258,
+      "rewards/real": -16.564544677734375,
+      "step": 760
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.534850640113798e-09,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -807.279296875,
+      "logps/real": -415.69586181640625,
+      "loss": 0.1756,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -52.691368103027344,
+      "rewards/margins": 36.51746368408203,
+      "rewards/real": -16.173904418945312,
+      "step": 770
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.422475106685633e-09,
+      "logits/generated": -Infinity,
+      "logits/real": -Infinity,
+      "logps/generated": -819.2388916015625,
+      "logps/real": -390.07391357421875,
+      "loss": 0.2143,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/generated": -52.7367057800293,
+      "rewards/margins": 36.12593460083008,
+      "rewards/real": -16.610774993896484,
+      "step": 780
+    },
+    {
+      "epoch": 1.0,
+      "step": 782,
+      "total_flos": 0.0,
+      "train_loss": 0.6284302195911938,
+      "train_runtime": 5860.6637,
+      "train_samples_per_second": 4.266,
+      "train_steps_per_second": 0.133
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}