Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: TTTXXX01/All_like-zephyr-7b-sft-full
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: IL_LSAll-7b-sft-full
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# IL_LSAll-7b-sft-full
+
+This model is a fine-tuned version of [TTTXXX01/All_like-zephyr-7b-sft-full](https://huggingface.co/TTTXXX01/All_like-zephyr-7b-sft-full) on an unknown dataset.
+
+## 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: 6
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 48
+- total_eval_batch_size: 16
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": -0.5441001898826946,
+    "train_runtime": 14755.3414,
+    "train_samples": 61135,
+    "train_samples_per_second": 4.143,
+    "train_steps_per_second": 0.086
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e4e7ff805619be660550bc85c03e15504d238231757b91311e0124ec1a19cb
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cac2f3f9a2d38e400c741b82314237447d7fd97fa9749fd1129b31606721b6
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a454211a6741359726e9744afd9081d62c55c372c0e8515fe0cf23538d482ff
+size 4540516344

model.safetensors.index.json

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

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": -0.5441001898826946,
+    "train_runtime": 14755.3414,
+    "train_samples": 61135,
+    "train_samples_per_second": 4.143,
+    "train_steps_per_second": 0.086
+}

trainer_state.json

@@ -0,0 +1,1962 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1274,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007849293563579278,
+      "grad_norm": 12.185681356731548,
+      "learning_rate": 3.90625e-09,
+      "logits/chosen": 5914.52099609375,
+      "logits/rejected": 2785.021484375,
+      "logps/chosen": -212.45889282226562,
+      "logps/rejected": -98.59669494628906,
+      "loss": -0.5,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.007849293563579277,
+      "grad_norm": 12.066996910892104,
+      "learning_rate": 3.9062499999999997e-08,
+      "logits/chosen": 4973.8837890625,
+      "logits/rejected": 4328.134765625,
+      "logps/chosen": -204.26583862304688,
+      "logps/rejected": -179.7384033203125,
+      "loss": -0.5002,
+      "rewards/accuracies": 0.5092592835426331,
+      "rewards/chosen": 0.01802830956876278,
+      "rewards/margins": 0.050810396671295166,
+      "rewards/rejected": -0.03278208523988724,
+      "step": 10
+    },
+    {
+      "epoch": 0.015698587127158554,
+      "grad_norm": 12.40225209927528,
+      "learning_rate": 7.812499999999999e-08,
+      "logits/chosen": 6083.919921875,
+      "logits/rejected": 4834.20361328125,
+      "logps/chosen": -217.2095489501953,
+      "logps/rejected": -196.75619506835938,
+      "loss": -0.4999,
+      "rewards/accuracies": 0.5416666269302368,
+      "rewards/chosen": 0.0016701116692274809,
+      "rewards/margins": 0.044297512620687485,
+      "rewards/rejected": -0.042627401649951935,
+      "step": 20
+    },
+    {
+      "epoch": 0.023547880690737835,
+      "grad_norm": 10.962805442919553,
+      "learning_rate": 1.1718749999999999e-07,
+      "logits/chosen": 6084.23046875,
+      "logits/rejected": 5104.7353515625,
+      "logps/chosen": -250.57443237304688,
+      "logps/rejected": -209.3799285888672,
+      "loss": -0.5004,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": -0.0020918771624565125,
+      "rewards/margins": 0.0802379846572876,
+      "rewards/rejected": -0.0823298767209053,
+      "step": 30
+    },
+    {
+      "epoch": 0.03139717425431711,
+      "grad_norm": 11.382523812855037,
+      "learning_rate": 1.5624999999999999e-07,
+      "logits/chosen": 5311.8466796875,
+      "logits/rejected": 4346.83544921875,
+      "logps/chosen": -211.97207641601562,
+      "logps/rejected": -181.73471069335938,
+      "loss": -0.5007,
+      "rewards/accuracies": 0.6083333492279053,
+      "rewards/chosen": 0.10717787593603134,
+      "rewards/margins": 0.15485556423664093,
+      "rewards/rejected": -0.04767768830060959,
+      "step": 40
+    },
+    {
+      "epoch": 0.03924646781789639,
+      "grad_norm": 11.553897270025715,
+      "learning_rate": 1.9531249999999998e-07,
+      "logits/chosen": 6424.97900390625,
+      "logits/rejected": 5042.32275390625,
+      "logps/chosen": -265.31195068359375,
+      "logps/rejected": -206.8114776611328,
+      "loss": -0.5014,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": 0.31464529037475586,
+      "rewards/margins": 0.4264959394931793,
+      "rewards/rejected": -0.11185060441493988,
+      "step": 50
+    },
+    {
+      "epoch": 0.04709576138147567,
+      "grad_norm": 11.145995154334138,
+      "learning_rate": 2.3437499999999998e-07,
+      "logits/chosen": 5484.03857421875,
+      "logits/rejected": 4559.96728515625,
+      "logps/chosen": -213.78250122070312,
+      "logps/rejected": -209.134765625,
+      "loss": -0.5026,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.22148728370666504,
+      "rewards/margins": 0.5561731457710266,
+      "rewards/rejected": -0.3346858322620392,
+      "step": 60
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 10.594540156239251,
+      "learning_rate": 2.734375e-07,
+      "logits/chosen": 5194.1630859375,
+      "logits/rejected": 4918.46630859375,
+      "logps/chosen": -178.32403564453125,
+      "logps/rejected": -177.35049438476562,
+      "loss": -0.504,
+      "rewards/accuracies": 0.658333420753479,
+      "rewards/chosen": 0.15687695145606995,
+      "rewards/margins": 0.7756644487380981,
+      "rewards/rejected": -0.6187874674797058,
+      "step": 70
+    },
+    {
+      "epoch": 0.06279434850863422,
+      "grad_norm": 10.745561073774455,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 5773.69873046875,
+      "logits/rejected": 5269.18994140625,
+      "logps/chosen": -196.75479125976562,
+      "logps/rejected": -182.96005249023438,
+      "loss": -0.508,
+      "rewards/accuracies": 0.6416666507720947,
+      "rewards/chosen": -0.18619374930858612,
+      "rewards/margins": 1.1833512783050537,
+      "rewards/rejected": -1.3695449829101562,
+      "step": 80
+    },
+    {
+      "epoch": 0.0706436420722135,
+      "grad_norm": 11.77104917639987,
+      "learning_rate": 3.5156249999999997e-07,
+      "logits/chosen": 6040.1220703125,
+      "logits/rejected": 5181.70849609375,
+      "logps/chosen": -219.984619140625,
+      "logps/rejected": -190.1697235107422,
+      "loss": -0.514,
+      "rewards/accuracies": 0.76666659116745,
+      "rewards/chosen": -1.10239577293396,
+      "rewards/margins": 4.623492240905762,
+      "rewards/rejected": -5.725888252258301,
+      "step": 90
+    },
+    {
+      "epoch": 0.07849293563579278,
+      "grad_norm": 11.742155692581838,
+      "learning_rate": 3.9062499999999997e-07,
+      "logits/chosen": 5969.318359375,
+      "logits/rejected": 5747.93798828125,
+      "logps/chosen": -213.4771728515625,
+      "logps/rejected": -208.06533813476562,
+      "loss": -0.513,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -3.246516466140747,
+      "rewards/margins": 5.377118110656738,
+      "rewards/rejected": -8.623634338378906,
+      "step": 100
+    },
+    {
+      "epoch": 0.08634222919937205,
+      "grad_norm": 10.563011580121817,
+      "learning_rate": 4.2968749999999996e-07,
+      "logits/chosen": 6467.24267578125,
+      "logits/rejected": 5287.21533203125,
+      "logps/chosen": -187.99197387695312,
+      "logps/rejected": -189.99929809570312,
+      "loss": -0.52,
+      "rewards/accuracies": 0.6750000715255737,
+      "rewards/chosen": -4.877109050750732,
+      "rewards/margins": 6.129989147186279,
+      "rewards/rejected": -11.007098197937012,
+      "step": 110
+    },
+    {
+      "epoch": 0.09419152276295134,
+      "grad_norm": 12.375994948676796,
+      "learning_rate": 4.6874999999999996e-07,
+      "logits/chosen": 6386.46826171875,
+      "logits/rejected": 5315.35107421875,
+      "logps/chosen": -209.4300079345703,
+      "logps/rejected": -211.3661651611328,
+      "loss": -0.5229,
+      "rewards/accuracies": 0.6583333611488342,
+      "rewards/chosen": -6.593257904052734,
+      "rewards/margins": 6.60781717300415,
+      "rewards/rejected": -13.201074600219727,
+      "step": 120
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 10.769412676611394,
+      "learning_rate": 4.999962424962166e-07,
+      "logits/chosen": 6304.9599609375,
+      "logits/rejected": 5837.7001953125,
+      "logps/chosen": -214.27236938476562,
+      "logps/rejected": -210.44900512695312,
+      "loss": -0.5258,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -4.4638848304748535,
+      "rewards/margins": 8.34054946899414,
+      "rewards/rejected": -12.804433822631836,
+      "step": 130
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 12.295935556547667,
+      "learning_rate": 4.998647417232375e-07,
+      "logits/chosen": 6149.7275390625,
+      "logits/rejected": 5416.37841796875,
+      "logps/chosen": -192.96670532226562,
+      "logps/rejected": -192.98519897460938,
+      "loss": -0.5265,
+      "rewards/accuracies": 0.6416666507720947,
+      "rewards/chosen": -7.299239158630371,
+      "rewards/margins": 8.094062805175781,
+      "rewards/rejected": -15.393301010131836,
+      "step": 140
+    },
+    {
+      "epoch": 0.11773940345368916,
+      "grad_norm": 14.539764643796898,
+      "learning_rate": 4.995454786965036e-07,
+      "logits/chosen": 6326.96337890625,
+      "logits/rejected": 5289.18701171875,
+      "logps/chosen": -207.80078125,
+      "logps/rejected": -189.2040252685547,
+      "loss": -0.5306,
+      "rewards/accuracies": 0.7166667580604553,
+      "rewards/chosen": -6.116393089294434,
+      "rewards/margins": 10.78992748260498,
+      "rewards/rejected": -16.906322479248047,
+      "step": 150
+    },
+    {
+      "epoch": 0.12558869701726844,
+      "grad_norm": 11.207640568489824,
+      "learning_rate": 4.990386933279972e-07,
+      "logits/chosen": 6298.8232421875,
+      "logits/rejected": 5626.849609375,
+      "logps/chosen": -205.1914520263672,
+      "logps/rejected": -215.720703125,
+      "loss": -0.5322,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -7.663259983062744,
+      "rewards/margins": 10.99985408782959,
+      "rewards/rejected": -18.66311264038086,
+      "step": 160
+    },
+    {
+      "epoch": 0.13343799058084774,
+      "grad_norm": 11.148522573070823,
+      "learning_rate": 4.983447664444096e-07,
+      "logits/chosen": 6521.455078125,
+      "logits/rejected": 5816.02978515625,
+      "logps/chosen": -216.96273803710938,
+      "logps/rejected": -212.0134735107422,
+      "loss": -0.5304,
+      "rewards/accuracies": 0.6500000357627869,
+      "rewards/chosen": -7.342079162597656,
+      "rewards/margins": 8.349851608276367,
+      "rewards/rejected": -15.691930770874023,
+      "step": 170
+    },
+    {
+      "epoch": 0.141287284144427,
+      "grad_norm": 11.676516090807922,
+      "learning_rate": 4.97464219500968e-07,
+      "logits/chosen": 5680.8671875,
+      "logits/rejected": 4962.62646484375,
+      "logps/chosen": -195.90188598632812,
+      "logps/rejected": -194.9904327392578,
+      "loss": -0.5311,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -7.374118804931641,
+      "rewards/margins": 9.45504379272461,
+      "rewards/rejected": -16.829160690307617,
+      "step": 180
+    },
+    {
+      "epoch": 0.14913657770800628,
+      "grad_norm": 11.938372210953599,
+      "learning_rate": 4.963977141895843e-07,
+      "logits/chosen": 5801.43798828125,
+      "logits/rejected": 4985.052734375,
+      "logps/chosen": -210.7730255126953,
+      "logps/rejected": -217.6445770263672,
+      "loss": -0.5382,
+      "rewards/accuracies": 0.7416667342185974,
+      "rewards/chosen": -7.014087677001953,
+      "rewards/margins": 19.390995025634766,
+      "rewards/rejected": -26.405080795288086,
+      "step": 190
+    },
+    {
+      "epoch": 0.15698587127158556,
+      "grad_norm": 13.331326878281788,
+      "learning_rate": 4.951460519416227e-07,
+      "logits/chosen": 5768.001953125,
+      "logits/rejected": 5333.7431640625,
+      "logps/chosen": -189.96151733398438,
+      "logps/rejected": -217.80111694335938,
+      "loss": -0.5373,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -7.417243957519531,
+      "rewards/margins": 13.712860107421875,
+      "rewards/rejected": -21.130104064941406,
+      "step": 200
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 12.088213484190312,
+      "learning_rate": 4.937101733256606e-07,
+      "logits/chosen": 5204.8251953125,
+      "logits/rejected": 4647.6201171875,
+      "logps/chosen": -165.14723205566406,
+      "logps/rejected": -181.01913452148438,
+      "loss": -0.5388,
+      "rewards/accuracies": 0.6416667699813843,
+      "rewards/chosen": -11.233977317810059,
+      "rewards/margins": 12.604203224182129,
+      "rewards/rejected": -23.83818244934082,
+      "step": 210
+    },
+    {
+      "epoch": 0.1726844583987441,
+      "grad_norm": 12.084984368162589,
+      "learning_rate": 4.920911573406924e-07,
+      "logits/chosen": 6338.34814453125,
+      "logits/rejected": 5404.54736328125,
+      "logps/chosen": -202.90597534179688,
+      "logps/rejected": -184.44300842285156,
+      "loss": -0.5367,
+      "rewards/accuracies": 0.7083333134651184,
+      "rewards/chosen": -6.569375514984131,
+      "rewards/margins": 13.876904487609863,
+      "rewards/rejected": -20.446279525756836,
+      "step": 220
+    },
+    {
+      "epoch": 0.18053375196232338,
+      "grad_norm": 12.304556304864667,
+      "learning_rate": 4.902902206053098e-07,
+      "logits/chosen": 5835.81005859375,
+      "logits/rejected": 5272.3916015625,
+      "logps/chosen": -195.09201049804688,
+      "logps/rejected": -200.99949645996094,
+      "loss": -0.5379,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -7.753264427185059,
+      "rewards/margins": 13.478750228881836,
+      "rewards/rejected": -21.232013702392578,
+      "step": 230
+    },
+    {
+      "epoch": 0.18838304552590268,
+      "grad_norm": 11.858671948962757,
+      "learning_rate": 4.883087164434672e-07,
+      "logits/chosen": 5319.9375,
+      "logits/rejected": 4253.84716796875,
+      "logps/chosen": -176.44406127929688,
+      "logps/rejected": -179.34446716308594,
+      "loss": -0.5415,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -8.815033912658691,
+      "rewards/margins": 15.839999198913574,
+      "rewards/rejected": -24.655033111572266,
+      "step": 240
+    },
+    {
+      "epoch": 0.19623233908948196,
+      "grad_norm": 12.860987570352677,
+      "learning_rate": 4.861481338675183e-07,
+      "logits/chosen": 6238.8427734375,
+      "logits/rejected": 5548.5595703125,
+      "logps/chosen": -178.11911010742188,
+      "logps/rejected": -211.85556030273438,
+      "loss": -0.5352,
+      "rewards/accuracies": 0.6999999284744263,
+      "rewards/chosen": -10.975238800048828,
+      "rewards/margins": 16.373638153076172,
+      "rewards/rejected": -27.348876953125,
+      "step": 250
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 13.77676710172865,
+      "learning_rate": 4.838100964592904e-07,
+      "logits/chosen": 6332.92919921875,
+      "logits/rejected": 5130.1845703125,
+      "logps/chosen": -207.98056030273438,
+      "logps/rejected": -187.11793518066406,
+      "loss": -0.5338,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -8.262109756469727,
+      "rewards/margins": 12.631866455078125,
+      "rewards/rejected": -20.89397430419922,
+      "step": 260
+    },
+    {
+      "epoch": 0.2119309262166405,
+      "grad_norm": 12.370375575916855,
+      "learning_rate": 4.812963611500339e-07,
+      "logits/chosen": 6204.505859375,
+      "logits/rejected": 6015.0693359375,
+      "logps/chosen": -207.0754852294922,
+      "logps/rejected": -211.184326171875,
+      "loss": -0.5453,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": -10.319671630859375,
+      "rewards/margins": 12.235608100891113,
+      "rewards/rejected": -22.55527687072754,
+      "step": 270
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 13.333747180731516,
+      "learning_rate": 4.786088169001671e-07,
+      "logits/chosen": 5350.53857421875,
+      "logits/rejected": 4659.34033203125,
+      "logps/chosen": -170.44593811035156,
+      "logps/rejected": -196.863525390625,
+      "loss": -0.5446,
+      "rewards/accuracies": 0.7666667699813843,
+      "rewards/chosen": -7.295041084289551,
+      "rewards/margins": 20.267045974731445,
+      "rewards/rejected": -27.562082290649414,
+      "step": 280
+    },
+    {
+      "epoch": 0.22762951334379905,
+      "grad_norm": 13.96823158237144,
+      "learning_rate": 4.7574948327980567e-07,
+      "logits/chosen": 7450.26806640625,
+      "logits/rejected": 5533.2412109375,
+      "logps/chosen": -243.9921112060547,
+      "logps/rejected": -212.14205932617188,
+      "loss": -0.5499,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -6.9636712074279785,
+      "rewards/margins": 22.662681579589844,
+      "rewards/rejected": -29.626354217529297,
+      "step": 290
+    },
+    {
+      "epoch": 0.23547880690737832,
+      "grad_norm": 12.558950857731215,
+      "learning_rate": 4.727205089511466e-07,
+      "logits/chosen": 5432.5947265625,
+      "logits/rejected": 5410.603515625,
+      "logps/chosen": -177.76187133789062,
+      "logps/rejected": -198.78128051757812,
+      "loss": -0.5399,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -10.289421081542969,
+      "rewards/margins": 18.305423736572266,
+      "rewards/rejected": -28.5948429107666,
+      "step": 300
+    },
+    {
+      "epoch": 0.24332810047095763,
+      "grad_norm": 14.201922916787394,
+      "learning_rate": 4.6952417005384247e-07,
+      "logits/chosen": 6099.38818359375,
+      "logits/rejected": 5433.0458984375,
+      "logps/chosen": -183.69717407226562,
+      "logps/rejected": -196.2397918701172,
+      "loss": -0.54,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -6.116464614868164,
+      "rewards/margins": 14.655021667480469,
+      "rewards/rejected": -20.771484375,
+      "step": 310
+    },
+    {
+      "epoch": 0.25117739403453687,
+      "grad_norm": 13.369021747374136,
+      "learning_rate": 4.661628684945851e-07,
+      "logits/chosen": 6102.36767578125,
+      "logits/rejected": 5295.1162109375,
+      "logps/chosen": -207.60568237304688,
+      "logps/rejected": -228.161865234375,
+      "loss": -0.541,
+      "rewards/accuracies": 0.6583333611488342,
+      "rewards/chosen": -6.5486907958984375,
+      "rewards/margins": 19.595294952392578,
+      "rewards/rejected": -26.14398765563965,
+      "step": 320
+    },
+    {
+      "epoch": 0.25902668759811615,
+      "grad_norm": 13.537470631829464,
+      "learning_rate": 4.626391301421782e-07,
+      "logits/chosen": 5880.90625,
+      "logits/rejected": 5355.83837890625,
+      "logps/chosen": -203.02908325195312,
+      "logps/rejected": -200.60757446289062,
+      "loss": -0.5351,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -8.575886726379395,
+      "rewards/margins": 14.708877563476562,
+      "rewards/rejected": -23.28476333618164,
+      "step": 330
+    },
+    {
+      "epoch": 0.2668759811616955,
+      "grad_norm": 12.219470457302588,
+      "learning_rate": 4.5895560292945996e-07,
+      "logits/chosen": 6148.09423828125,
+      "logits/rejected": 6284.05419921875,
+      "logps/chosen": -199.61947631835938,
+      "logps/rejected": -241.6748504638672,
+      "loss": -0.5415,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -5.761203289031982,
+      "rewards/margins": 15.546130180358887,
+      "rewards/rejected": -21.30733299255371,
+      "step": 340
+    },
+    {
+      "epoch": 0.27472527472527475,
+      "grad_norm": 14.312166127291615,
+      "learning_rate": 4.5511505486349865e-07,
+      "logits/chosen": 6496.5771484375,
+      "logits/rejected": 5905.1181640625,
+      "logps/chosen": -199.84910583496094,
+      "logps/rejected": -234.73599243164062,
+      "loss": -0.548,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -5.023402214050293,
+      "rewards/margins": 22.890575408935547,
+      "rewards/rejected": -27.913976669311523,
+      "step": 350
+    },
+    {
+      "epoch": 0.282574568288854,
+      "grad_norm": 14.088746309162621,
+      "learning_rate": 4.5112037194555876e-07,
+      "logits/chosen": 6001.92578125,
+      "logits/rejected": 5925.07861328125,
+      "logps/chosen": -190.96304321289062,
+      "logps/rejected": -233.9935760498047,
+      "loss": -0.543,
+      "rewards/accuracies": 0.7333332896232605,
+      "rewards/chosen": -13.039606094360352,
+      "rewards/margins": 21.672157287597656,
+      "rewards/rejected": -34.711761474609375,
+      "step": 360
+    },
+    {
+      "epoch": 0.2904238618524333,
+      "grad_norm": 14.758996475483764,
+      "learning_rate": 4.4697455600239863e-07,
+      "logits/chosen": 5456.59375,
+      "logits/rejected": 5158.630859375,
+      "logps/chosen": -194.8301544189453,
+      "logps/rejected": -197.39712524414062,
+      "loss": -0.5361,
+      "rewards/accuracies": 0.6916666626930237,
+      "rewards/chosen": -10.408088684082031,
+      "rewards/margins": 18.91793441772461,
+      "rewards/rejected": -29.326025009155273,
+      "step": 370
+    },
+    {
+      "epoch": 0.29827315541601257,
+      "grad_norm": 14.815915118950619,
+      "learning_rate": 4.426807224305315e-07,
+      "logits/chosen": 6503.11962890625,
+      "logits/rejected": 5408.39306640625,
+      "logps/chosen": -235.3462677001953,
+      "logps/rejected": -212.32003784179688,
+      "loss": -0.546,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -7.005249977111816,
+      "rewards/margins": 22.305225372314453,
+      "rewards/rejected": -29.310476303100586,
+      "step": 380
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 13.698299560417563,
+      "learning_rate": 4.3824209785514326e-07,
+      "logits/chosen": 6644.3505859375,
+      "logits/rejected": 5104.09521484375,
+      "logps/chosen": -221.2438201904297,
+      "logps/rejected": -218.32943725585938,
+      "loss": -0.5524,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -5.750358581542969,
+      "rewards/margins": 32.725975036621094,
+      "rewards/rejected": -38.47633743286133,
+      "step": 390
+    },
+    {
+      "epoch": 0.3139717425431711,
+      "grad_norm": 13.596298740826661,
+      "learning_rate": 4.3366201770542687e-07,
+      "logits/chosen": 5721.71435546875,
+      "logits/rejected": 5618.02978515625,
+      "logps/chosen": -200.8018341064453,
+      "logps/rejected": -226.2516632080078,
+      "loss": -0.5414,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -10.013228416442871,
+      "rewards/margins": 27.498947143554688,
+      "rewards/rejected": -37.51217269897461,
+      "step": 400
+    },
+    {
+      "epoch": 0.3218210361067504,
+      "grad_norm": 21.60392631215127,
+      "learning_rate": 4.2894392370815567e-07,
+      "logits/chosen": 6170.86328125,
+      "logits/rejected": 5508.14208984375,
+      "logps/chosen": -222.9990234375,
+      "logps/rejected": -256.97540283203125,
+      "loss": -0.5648,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -10.512117385864258,
+      "rewards/margins": 38.01092529296875,
+      "rewards/rejected": -48.52304458618164,
+      "step": 410
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 19.0790120070253,
+      "learning_rate": 4.2409136130137845e-07,
+      "logits/chosen": 5799.7158203125,
+      "logits/rejected": 5273.5751953125,
+      "logps/chosen": -217.6487274169922,
+      "logps/rejected": -227.30331420898438,
+      "loss": -0.5479,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -13.61878776550293,
+      "rewards/margins": 32.44309997558594,
+      "rewards/rejected": -46.0618896484375,
+      "step": 420
+    },
+    {
+      "epoch": 0.33751962323390894,
+      "grad_norm": 14.50200341648645,
+      "learning_rate": 4.1910797697018017e-07,
+      "logits/chosen": 5581.63720703125,
+      "logits/rejected": 4674.400390625,
+      "logps/chosen": -190.4328155517578,
+      "logps/rejected": -197.7171173095703,
+      "loss": -0.5513,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -10.687819480895996,
+      "rewards/margins": 25.796178817749023,
+      "rewards/rejected": -36.48400115966797,
+      "step": 430
+    },
+    {
+      "epoch": 0.3453689167974882,
+      "grad_norm": 14.931746475331163,
+      "learning_rate": 4.1399751550651084e-07,
+      "logits/chosen": 5941.59814453125,
+      "logits/rejected": 5881.9892578125,
+      "logps/chosen": -192.48472595214844,
+      "logps/rejected": -226.8599853515625,
+      "loss": -0.5495,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -10.09138011932373,
+      "rewards/margins": 25.08499526977539,
+      "rewards/rejected": -35.17637634277344,
+      "step": 440
+    },
+    {
+      "epoch": 0.3532182103610675,
+      "grad_norm": 14.476601288378774,
+      "learning_rate": 4.087638171951401e-07,
+      "logits/chosen": 6844.02978515625,
+      "logits/rejected": 4965.66552734375,
+      "logps/chosen": -215.19436645507812,
+      "logps/rejected": -201.01358032226562,
+      "loss": -0.5446,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -6.425619602203369,
+      "rewards/margins": 31.595306396484375,
+      "rewards/rejected": -38.02092361450195,
+      "step": 450
+    },
+    {
+      "epoch": 0.36106750392464676,
+      "grad_norm": 12.493477466659453,
+      "learning_rate": 4.034108149278543e-07,
+      "logits/chosen": 7059.74365234375,
+      "logits/rejected": 5534.33447265625,
+      "logps/chosen": -259.2933654785156,
+      "logps/rejected": -219.4051971435547,
+      "loss": -0.549,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -8.861111640930176,
+      "rewards/margins": 20.336048126220703,
+      "rewards/rejected": -29.197154998779297,
+      "step": 460
+    },
+    {
+      "epoch": 0.36891679748822603,
+      "grad_norm": 14.398041055949756,
+      "learning_rate": 3.979425312480629e-07,
+      "logits/chosen": 6101.0927734375,
+      "logits/rejected": 5368.69140625,
+      "logps/chosen": -222.6365203857422,
+      "logps/rejected": -240.66592407226562,
+      "loss": -0.5474,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -10.3717622756958,
+      "rewards/margins": 27.727893829345703,
+      "rewards/rejected": -38.09965515136719,
+      "step": 470
+    },
+    {
+      "epoch": 0.37676609105180536,
+      "grad_norm": 13.515928817603175,
+      "learning_rate": 3.923630753280357e-07,
+      "logits/chosen": 6586.9609375,
+      "logits/rejected": 5732.6962890625,
+      "logps/chosen": -218.5810089111328,
+      "logps/rejected": -215.1974334716797,
+      "loss": -0.547,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -11.185822486877441,
+      "rewards/margins": 29.6158390045166,
+      "rewards/rejected": -40.801658630371094,
+      "step": 480
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 17.390744031191396,
+      "learning_rate": 3.866766398810424e-07,
+      "logits/chosen": 6174.2861328125,
+      "logits/rejected": 5929.84326171875,
+      "logps/chosen": -180.99270629882812,
+      "logps/rejected": -239.779541015625,
+      "loss": -0.5608,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -4.384220123291016,
+      "rewards/margins": 33.371002197265625,
+      "rewards/rejected": -37.75522232055664,
+      "step": 490
+    },
+    {
+      "epoch": 0.3924646781789639,
+      "grad_norm": 20.545482385498747,
+      "learning_rate": 3.8088749801071496e-07,
+      "logits/chosen": 6699.80078125,
+      "logits/rejected": 5181.845703125,
+      "logps/chosen": -241.4040985107422,
+      "logps/rejected": -258.91363525390625,
+      "loss": -0.5433,
+      "rewards/accuracies": 0.73333340883255,
+      "rewards/chosen": -19.450458526611328,
+      "rewards/margins": 36.94696807861328,
+      "rewards/rejected": -56.397430419921875,
+      "step": 500
+    },
+    {
+      "epoch": 0.4003139717425432,
+      "grad_norm": 15.348191714605942,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 5331.91162109375,
+      "logits/rejected": 4749.47265625,
+      "logps/chosen": -195.63552856445312,
+      "logps/rejected": -202.39199829101562,
+      "loss": -0.5533,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -6.15253210067749,
+      "rewards/margins": 29.87417221069336,
+      "rewards/rejected": -36.02670669555664,
+      "step": 510
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 17.179270022544692,
+      "learning_rate": 3.6901857004211443e-07,
+      "logits/chosen": 5678.765625,
+      "logits/rejected": 5301.3427734375,
+      "logps/chosen": -209.762939453125,
+      "logps/rejected": -227.5038604736328,
+      "loss": -0.5304,
+      "rewards/accuracies": 0.6833332777023315,
+      "rewards/chosen": -11.296924591064453,
+      "rewards/margins": 20.41892433166504,
+      "rewards/rejected": -31.71584701538086,
+      "step": 520
+    },
+    {
+      "epoch": 0.41601255886970173,
+      "grad_norm": 12.968043224968394,
+      "learning_rate": 3.6294770291596076e-07,
+      "logits/chosen": 6412.17138671875,
+      "logits/rejected": 5298.6142578125,
+      "logps/chosen": -220.1424102783203,
+      "logps/rejected": -227.05404663085938,
+      "loss": -0.5559,
+      "rewards/accuracies": 0.6666666269302368,
+      "rewards/chosen": -7.219654083251953,
+      "rewards/margins": 21.074071884155273,
+      "rewards/rejected": -28.29372787475586,
+      "step": 530
+    },
+    {
+      "epoch": 0.423861852433281,
+      "grad_norm": 21.703435125964788,
+      "learning_rate": 3.5679196060850034e-07,
+      "logits/chosen": 6090.72607421875,
+      "logits/rejected": 5481.96728515625,
+      "logps/chosen": -220.23135375976562,
+      "logps/rejected": -224.384521484375,
+      "loss": -0.5486,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -9.41352653503418,
+      "rewards/margins": 26.732208251953125,
+      "rewards/rejected": -36.14573669433594,
+      "step": 540
+    },
+    {
+      "epoch": 0.4317111459968603,
+      "grad_norm": 37.52988937079133,
+      "learning_rate": 3.505559688866229e-07,
+      "logits/chosen": 5888.26220703125,
+      "logits/rejected": 5514.62841796875,
+      "logps/chosen": -225.4257049560547,
+      "logps/rejected": -265.7478332519531,
+      "loss": -0.5531,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -10.685269355773926,
+      "rewards/margins": 29.998464584350586,
+      "rewards/rejected": -40.683738708496094,
+      "step": 550
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 16.990632916112638,
+      "learning_rate": 3.4424441382108826e-07,
+      "logits/chosen": 5950.71142578125,
+      "logits/rejected": 5591.7197265625,
+      "logps/chosen": -216.213134765625,
+      "logps/rejected": -236.20703125,
+      "loss": -0.544,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -12.937848091125488,
+      "rewards/margins": 30.05996322631836,
+      "rewards/rejected": -42.99781036376953,
+      "step": 560
+    },
+    {
+      "epoch": 0.4474097331240188,
+      "grad_norm": 21.823795774201802,
+      "learning_rate": 3.378620382651523e-07,
+      "logits/chosen": 6279.9443359375,
+      "logits/rejected": 5810.06005859375,
+      "logps/chosen": -254.17337036132812,
+      "logps/rejected": -264.60821533203125,
+      "loss": -0.5522,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -11.213506698608398,
+      "rewards/margins": 29.624225616455078,
+      "rewards/rejected": -40.837730407714844,
+      "step": 570
+    },
+    {
+      "epoch": 0.4552590266875981,
+      "grad_norm": 14.737833568834182,
+      "learning_rate": 3.314136382905234e-07,
+      "logits/chosen": 6228.8447265625,
+      "logits/rejected": 5667.69580078125,
+      "logps/chosen": -219.33993530273438,
+      "logps/rejected": -250.21707153320312,
+      "loss": -0.5449,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -6.924456596374512,
+      "rewards/margins": 29.981273651123047,
+      "rewards/rejected": -36.90573501586914,
+      "step": 580
+    },
+    {
+      "epoch": 0.4631083202511774,
+      "grad_norm": 13.760212196324753,
+      "learning_rate": 3.249040595833274e-07,
+      "logits/chosen": 6781.17822265625,
+      "logits/rejected": 5766.2646484375,
+      "logps/chosen": -239.05776977539062,
+      "logps/rejected": -213.7412872314453,
+      "loss": -0.5554,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -7.3319220542907715,
+      "rewards/margins": 27.55051040649414,
+      "rewards/rejected": -34.88243103027344,
+      "step": 590
+    },
+    {
+      "epoch": 0.47095761381475665,
+      "grad_norm": 19.441232852710126,
+      "learning_rate": 3.1833819380279023e-07,
+      "logits/chosen": 6427.10107421875,
+      "logits/rejected": 5508.02001953125,
+      "logps/chosen": -188.13037109375,
+      "logps/rejected": -230.70938110351562,
+      "loss": -0.5525,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -10.582036972045898,
+      "rewards/margins": 30.44106674194336,
+      "rewards/rejected": -41.023101806640625,
+      "step": 600
+    },
+    {
+      "epoch": 0.478806907378336,
+      "grad_norm": 13.388579418872117,
+      "learning_rate": 3.11720974905373e-07,
+      "logits/chosen": 6165.43896484375,
+      "logits/rejected": 5416.3076171875,
+      "logps/chosen": -216.6073455810547,
+      "logps/rejected": -230.8435516357422,
+      "loss": -0.56,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -10.489218711853027,
+      "rewards/margins": 34.93179702758789,
+      "rewards/rejected": -45.421016693115234,
+      "step": 610
+    },
+    {
+      "epoch": 0.48665620094191525,
+      "grad_norm": 18.107686999639345,
+      "learning_rate": 3.0505737543712275e-07,
+      "logits/chosen": 5264.59521484375,
+      "logits/rejected": 4359.83251953125,
+      "logps/chosen": -194.50704956054688,
+      "logps/rejected": -204.3115692138672,
+      "loss": -0.5575,
+      "rewards/accuracies": 0.8166667222976685,
+      "rewards/chosen": -10.748395919799805,
+      "rewards/margins": 32.46430206298828,
+      "rewards/rejected": -43.21269607543945,
+      "step": 620
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 16.23681720440276,
+      "learning_rate": 2.9835240279702513e-07,
+      "logits/chosen": 6860.98046875,
+      "logits/rejected": 5905.08056640625,
+      "logps/chosen": -250.0574188232422,
+      "logps/rejected": -243.52294921875,
+      "loss": -0.56,
+      "rewards/accuracies": 0.7833333015441895,
+      "rewards/chosen": -7.241453647613525,
+      "rewards/margins": 42.033416748046875,
+      "rewards/rejected": -49.274871826171875,
+      "step": 630
+    },
+    {
+      "epoch": 0.5023547880690737,
+      "grad_norm": 15.133905436958523,
+      "learning_rate": 2.9161109547416667e-07,
+      "logits/chosen": 6525.08740234375,
+      "logits/rejected": 5607.15185546875,
+      "logps/chosen": -222.1215362548828,
+      "logps/rejected": -249.20364379882812,
+      "loss": -0.5586,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -11.359973907470703,
+      "rewards/margins": 23.3347225189209,
+      "rewards/rejected": -34.69469451904297,
+      "step": 640
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 16.011606806242707,
+      "learning_rate": 2.848385192615339e-07,
+      "logits/chosen": 5628.36181640625,
+      "logits/rejected": 4637.24462890625,
+      "logps/chosen": -205.99490356445312,
+      "logps/rejected": -203.79971313476562,
+      "loss": -0.5518,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -9.655582427978516,
+      "rewards/margins": 25.41636848449707,
+      "rewards/rejected": -35.07195281982422,
+      "step": 650
+    },
+    {
+      "epoch": 0.5180533751962323,
+      "grad_norm": 21.247801665890794,
+      "learning_rate": 2.780397634492949e-07,
+      "logits/chosen": 6310.8505859375,
+      "logits/rejected": 5097.1552734375,
+      "logps/chosen": -227.1197509765625,
+      "logps/rejected": -238.29598999023438,
+      "loss": -0.5485,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -9.73323917388916,
+      "rewards/margins": 40.615299224853516,
+      "rewards/rejected": -50.34853744506836,
+      "step": 660
+    },
+    {
+      "epoch": 0.5259026687598116,
+      "grad_norm": 15.560809488629776,
+      "learning_rate": 2.71219937000424e-07,
+      "logits/chosen": 6286.98486328125,
+      "logits/rejected": 5196.23583984375,
+      "logps/chosen": -220.25863647460938,
+      "logps/rejected": -234.5564422607422,
+      "loss": -0.5473,
+      "rewards/accuracies": 0.8166667222976685,
+      "rewards/chosen": -13.499173164367676,
+      "rewards/margins": 32.202857971191406,
+      "rewards/rejected": -45.702030181884766,
+      "step": 670
+    },
+    {
+      "epoch": 0.533751962323391,
+      "grad_norm": 14.170981357167607,
+      "learning_rate": 2.6438416471154273e-07,
+      "logits/chosen": 6083.7236328125,
+      "logits/rejected": 5118.7060546875,
+      "logps/chosen": -222.4500274658203,
+      "logps/rejected": -222.7382354736328,
+      "loss": -0.5508,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -8.788731575012207,
+      "rewards/margins": 34.72281265258789,
+      "rewards/rejected": -43.51154708862305,
+      "step": 680
+    },
+    {
+      "epoch": 0.5416012558869702,
+      "grad_norm": 13.47806294145218,
+      "learning_rate": 2.5753758336186326e-07,
+      "logits/chosen": 6007.140625,
+      "logits/rejected": 5543.3837890625,
+      "logps/chosen": -219.5069580078125,
+      "logps/rejected": -257.30035400390625,
+      "loss": -0.5561,
+      "rewards/accuracies": 0.7416667342185974,
+      "rewards/chosen": -10.400491714477539,
+      "rewards/margins": 30.703176498413086,
+      "rewards/rejected": -41.10367202758789,
+      "step": 690
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 14.319715146996487,
+      "learning_rate": 2.5068533785312666e-07,
+      "logits/chosen": 5713.2421875,
+      "logits/rejected": 5524.46728515625,
+      "logps/chosen": -200.09414672851562,
+      "logps/rejected": -227.26785278320312,
+      "loss": -0.5387,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -10.833822250366211,
+      "rewards/margins": 29.460071563720703,
+      "rewards/rejected": -40.29389190673828,
+      "step": 700
+    },
+    {
+      "epoch": 0.5572998430141287,
+      "grad_norm": 15.375895555824917,
+      "learning_rate": 2.4383257734343794e-07,
+      "logits/chosen": 5675.8701171875,
+      "logits/rejected": 5728.0244140625,
+      "logps/chosen": -204.74752807617188,
+      "logps/rejected": -241.16943359375,
+      "loss": -0.5554,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -10.83613395690918,
+      "rewards/margins": 27.712646484375,
+      "rewards/rejected": -38.54877853393555,
+      "step": 710
+    },
+    {
+      "epoch": 0.565149136577708,
+      "grad_norm": 14.873727955111258,
+      "learning_rate": 2.3698445137790258e-07,
+      "logits/chosen": 6093.0908203125,
+      "logits/rejected": 5287.7705078125,
+      "logps/chosen": -226.853271484375,
+      "logps/rejected": -238.8446502685547,
+      "loss": -0.5478,
+      "rewards/accuracies": 0.7833333015441895,
+      "rewards/chosen": -7.8500471115112305,
+      "rewards/margins": 31.229473114013672,
+      "rewards/rejected": -39.07952117919922,
+      "step": 720
+    },
+    {
+      "epoch": 0.5729984301412873,
+      "grad_norm": 17.247561991897758,
+      "learning_rate": 2.3014610601897157e-07,
+      "logits/chosen": 6625.6201171875,
+      "logits/rejected": 5123.14208984375,
+      "logps/chosen": -237.73007202148438,
+      "logps/rejected": -221.32418823242188,
+      "loss": -0.5595,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -12.584187507629395,
+      "rewards/margins": 33.66630172729492,
+      "rewards/rejected": -46.25048828125,
+      "step": 730
+    },
+    {
+      "epoch": 0.5808477237048666,
+      "grad_norm": 19.18591397361123,
+      "learning_rate": 2.2332267997940513e-07,
+      "logits/chosen": 5518.5419921875,
+      "logits/rejected": 4722.01513671875,
+      "logps/chosen": -199.68359375,
+      "logps/rejected": -204.318359375,
+      "loss": -0.5589,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -7.2591447830200195,
+      "rewards/margins": 34.41317367553711,
+      "rewards/rejected": -41.672325134277344,
+      "step": 740
+    },
+    {
+      "epoch": 0.5886970172684458,
+      "grad_norm": 13.735789569741188,
+      "learning_rate": 2.1651930076075723e-07,
+      "logits/chosen": 6000.32470703125,
+      "logits/rejected": 5473.8232421875,
+      "logps/chosen": -192.8706817626953,
+      "logps/rejected": -205.87020874023438,
+      "loss": -0.5484,
+      "rewards/accuracies": 0.7166667580604553,
+      "rewards/chosen": -12.444730758666992,
+      "rewards/margins": 26.331233978271484,
+      "rewards/rejected": -38.775962829589844,
+      "step": 750
+    },
+    {
+      "epoch": 0.5965463108320251,
+      "grad_norm": 14.884916482785034,
+      "learning_rate": 2.0974108080028692e-07,
+      "logits/chosen": 6278.75048828125,
+      "logits/rejected": 5003.58544921875,
+      "logps/chosen": -215.50863647460938,
+      "logps/rejected": -215.87338256835938,
+      "loss": -0.5446,
+      "rewards/accuracies": 0.7083333134651184,
+      "rewards/chosen": -12.257668495178223,
+      "rewards/margins": 29.0852108001709,
+      "rewards/rejected": -41.34288024902344,
+      "step": 760
+    },
+    {
+      "epoch": 0.6043956043956044,
+      "grad_norm": 22.408784444588175,
+      "learning_rate": 2.0299311362918773e-07,
+      "logits/chosen": 6477.56787109375,
+      "logits/rejected": 5610.052734375,
+      "logps/chosen": -241.07846069335938,
+      "logps/rejected": -267.69708251953125,
+      "loss": -0.5442,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -11.34480094909668,
+      "rewards/margins": 32.4921875,
+      "rewards/rejected": -43.83699035644531,
+      "step": 770
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 13.15499328897201,
+      "learning_rate": 1.962804700450265e-07,
+      "logits/chosen": 6326.91259765625,
+      "logits/rejected": 6053.4404296875,
+      "logps/chosen": -225.9958953857422,
+      "logps/rejected": -271.9791564941406,
+      "loss": -0.5457,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -9.890580177307129,
+      "rewards/margins": 24.70089340209961,
+      "rewards/rejected": -34.591468811035156,
+      "step": 780
+    },
+    {
+      "epoch": 0.6200941915227629,
+      "grad_norm": 18.37743177954423,
+      "learning_rate": 1.8960819430126334e-07,
+      "logits/chosen": 5896.37841796875,
+      "logits/rejected": 5250.25146484375,
+      "logps/chosen": -212.64840698242188,
+      "logps/rejected": -240.15286254882812,
+      "loss": -0.5526,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -14.517425537109375,
+      "rewards/margins": 37.03769302368164,
+      "rewards/rejected": -51.55511474609375,
+      "step": 790
+    },
+    {
+      "epoch": 0.6279434850863422,
+      "grad_norm": 15.962566634301062,
+      "learning_rate": 1.8298130031671972e-07,
+      "logits/chosen": 5897.72021484375,
+      "logits/rejected": 5196.263671875,
+      "logps/chosen": -231.2862091064453,
+      "logps/rejected": -256.14483642578125,
+      "loss": -0.5427,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -14.563385009765625,
+      "rewards/margins": 28.883220672607422,
+      "rewards/rejected": -43.44660568237305,
+      "step": 800
+    },
+    {
+      "epoch": 0.6357927786499215,
+      "grad_norm": 14.503187832917975,
+      "learning_rate": 1.7640476790784075e-07,
+      "logits/chosen": 5457.9208984375,
+      "logits/rejected": 4929.38916015625,
+      "logps/chosen": -212.62448120117188,
+      "logps/rejected": -262.00335693359375,
+      "loss": -0.5505,
+      "rewards/accuracies": 0.7499999403953552,
+      "rewards/chosen": -10.169076919555664,
+      "rewards/margins": 30.537002563476562,
+      "rewards/rejected": -40.706077575683594,
+      "step": 810
+    },
+    {
+      "epoch": 0.6436420722135008,
+      "grad_norm": 17.287039922914133,
+      "learning_rate": 1.6988353904658492e-07,
+      "logits/chosen": 5933.09375,
+      "logits/rejected": 4622.87109375,
+      "logps/chosen": -228.77828979492188,
+      "logps/rejected": -208.31448364257812,
+      "loss": -0.556,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -7.563757419586182,
+      "rewards/margins": 32.06237030029297,
+      "rewards/rejected": -39.62612533569336,
+      "step": 820
+    },
+    {
+      "epoch": 0.6514913657770801,
+      "grad_norm": 16.00623751669361,
+      "learning_rate": 1.634225141467513e-07,
+      "logits/chosen": 5868.5166015625,
+      "logits/rejected": 5272.09912109375,
+      "logps/chosen": -217.6871795654297,
+      "logps/rejected": -241.2273712158203,
+      "loss": -0.5533,
+      "rewards/accuracies": 0.7416667342185974,
+      "rewards/chosen": -13.501172065734863,
+      "rewards/margins": 35.271339416503906,
+      "rewards/rejected": -48.77251052856445,
+      "step": 830
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 13.65824185805484,
+      "learning_rate": 1.570265483815364e-07,
+      "logits/chosen": 6410.0361328125,
+      "logits/rejected": 5289.599609375,
+      "logps/chosen": -243.1864471435547,
+      "logps/rejected": -254.82406616210938,
+      "loss": -0.5502,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -15.856649398803711,
+      "rewards/margins": 26.174245834350586,
+      "rewards/rejected": -42.03089141845703,
+      "step": 840
+    },
+    {
+      "epoch": 0.6671899529042387,
+      "grad_norm": 14.96256454286525,
+      "learning_rate": 1.5070044803508691e-07,
+      "logits/chosen": 5922.5771484375,
+      "logits/rejected": 5358.466796875,
+      "logps/chosen": -228.34841918945312,
+      "logps/rejected": -248.4814910888672,
+      "loss": -0.5573,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -12.870938301086426,
+      "rewards/margins": 35.15522003173828,
+      "rewards/rejected": -48.02615737915039,
+      "step": 850
+    },
+    {
+      "epoch": 0.6750392464678179,
+      "grad_norm": 14.889400880268978,
+      "learning_rate": 1.444489668907914e-07,
+      "logits/chosen": 6385.53466796875,
+      "logits/rejected": 5459.19091796875,
+      "logps/chosen": -257.6268310546875,
+      "logps/rejected": -245.7576446533203,
+      "loss": -0.5477,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -9.85617733001709,
+      "rewards/margins": 33.21961212158203,
+      "rewards/rejected": -43.07579803466797,
+      "step": 860
+    },
+    {
+      "epoch": 0.6828885400313972,
+      "grad_norm": 13.291251228226638,
+      "learning_rate": 1.3827680265902232e-07,
+      "logits/chosen": 6342.3896484375,
+      "logits/rejected": 5289.41796875,
+      "logps/chosen": -241.23410034179688,
+      "logps/rejected": -240.6619873046875,
+      "loss": -0.5514,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -11.137380599975586,
+      "rewards/margins": 28.83567237854004,
+      "rewards/rejected": -39.973052978515625,
+      "step": 870
+    },
+    {
+      "epoch": 0.6907378335949764,
+      "grad_norm": 16.523056356741357,
+      "learning_rate": 1.3218859344701632e-07,
+      "logits/chosen": 5571.25390625,
+      "logits/rejected": 5356.0625,
+      "logps/chosen": -220.6587677001953,
+      "logps/rejected": -270.5399169921875,
+      "loss": -0.5457,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -10.14782428741455,
+      "rewards/margins": 28.80292320251465,
+      "rewards/rejected": -38.950748443603516,
+      "step": 880
+    },
+    {
+      "epoch": 0.6985871271585558,
+      "grad_norm": 17.16912370914084,
+      "learning_rate": 1.2618891427354172e-07,
+      "logits/chosen": 6568.57421875,
+      "logits/rejected": 5379.8818359375,
+      "logps/chosen": -264.95001220703125,
+      "logps/rejected": -252.56497192382812,
+      "loss": -0.5498,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -7.353941917419434,
+      "rewards/margins": 33.43050765991211,
+      "rewards/rejected": -40.784446716308594,
+      "step": 890
+    },
+    {
+      "epoch": 0.706436420722135,
+      "grad_norm": 14.805310374425751,
+      "learning_rate": 1.202822736309758e-07,
+      "logits/chosen": 5562.001953125,
+      "logits/rejected": 5189.39013671875,
+      "logps/chosen": -214.02035522460938,
+      "logps/rejected": -252.0713653564453,
+      "loss": -0.5492,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -9.671173095703125,
+      "rewards/margins": 31.970129013061523,
+      "rewards/rejected": -41.64129638671875,
+      "step": 900
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 15.154490017250051,
+      "learning_rate": 1.1447311009737299e-07,
+      "logits/chosen": 5476.24072265625,
+      "logits/rejected": 5228.48291015625,
+      "logps/chosen": -221.74267578125,
+      "logps/rejected": -256.24432373046875,
+      "loss": -0.5496,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -13.516392707824707,
+      "rewards/margins": 34.79946517944336,
+      "rewards/rejected": -48.315860748291016,
+      "step": 910
+    },
+    {
+      "epoch": 0.7221350078492935,
+      "grad_norm": 22.407408345422997,
+      "learning_rate": 1.0876578900107053e-07,
+      "logits/chosen": 6060.7919921875,
+      "logits/rejected": 5049.7998046875,
+      "logps/chosen": -243.87020874023438,
+      "logps/rejected": -245.1348114013672,
+      "loss": -0.5507,
+      "rewards/accuracies": 0.7916666865348816,
+      "rewards/chosen": -11.448633193969727,
+      "rewards/margins": 35.54388427734375,
+      "rewards/rejected": -46.992515563964844,
+      "step": 920
+    },
+    {
+      "epoch": 0.7299843014128728,
+      "grad_norm": 14.713347007112848,
+      "learning_rate": 1.0316459914033793e-07,
+      "logits/chosen": 5965.28076171875,
+      "logits/rejected": 4541.7861328125,
+      "logps/chosen": -251.3324737548828,
+      "logps/rejected": -233.15658569335938,
+      "loss": -0.5469,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -15.343559265136719,
+      "rewards/margins": 31.8887939453125,
+      "rewards/rejected": -47.23234939575195,
+      "step": 930
+    },
+    {
+      "epoch": 0.7378335949764521,
+      "grad_norm": 16.078089093379223,
+      "learning_rate": 9.767374956053584e-08,
+      "logits/chosen": 5780.9345703125,
+      "logits/rejected": 5092.5830078125,
+      "logps/chosen": -230.3660888671875,
+      "logps/rejected": -252.21774291992188,
+      "loss": -0.5496,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -12.072437286376953,
+      "rewards/margins": 35.165443420410156,
+      "rewards/rejected": -47.237876892089844,
+      "step": 940
+    },
+    {
+      "epoch": 0.7456828885400314,
+      "grad_norm": 16.261901912135954,
+      "learning_rate": 9.229736639120561e-08,
+      "logits/chosen": 5962.2880859375,
+      "logits/rejected": 5526.39306640625,
+      "logps/chosen": -228.35769653320312,
+      "logps/rejected": -246.65869140625,
+      "loss": -0.5429,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -10.55649471282959,
+      "rewards/margins": 21.94769287109375,
+      "rewards/rejected": -32.504188537597656,
+      "step": 950
+    },
+    {
+      "epoch": 0.7535321821036107,
+      "grad_norm": 13.221689149992935,
+      "learning_rate": 8.70394897454659e-08,
+      "logits/chosen": 5809.796875,
+      "logits/rejected": 5207.8203125,
+      "logps/chosen": -224.7841796875,
+      "logps/rejected": -238.98696899414062,
+      "loss": -0.5546,
+      "rewards/accuracies": 0.8166667222976685,
+      "rewards/chosen": -6.355766296386719,
+      "rewards/margins": 30.154870986938477,
+      "rewards/rejected": -36.51063537597656,
+      "step": 960
+    },
+    {
+      "epoch": 0.7613814756671899,
+      "grad_norm": 15.744789799259141,
+      "learning_rate": 8.19040706840472e-08,
+      "logits/chosen": 5915.970703125,
+      "logits/rejected": 4988.2001953125,
+      "logps/chosen": -249.45468139648438,
+      "logps/rejected": -252.91500854492188,
+      "loss": -0.5573,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -9.234709739685059,
+      "rewards/margins": 36.98971939086914,
+      "rewards/rejected": -46.22443389892578,
+      "step": 970
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 14.041623563140766,
+      "learning_rate": 7.689496824624525e-08,
+      "logits/chosen": 5622.8994140625,
+      "logits/rejected": 4569.49462890625,
+      "logps/chosen": -236.6791229248047,
+      "logps/rejected": -245.09487915039062,
+      "loss": -0.5557,
+      "rewards/accuracies": 0.8166666030883789,
+      "rewards/chosen": -7.862542152404785,
+      "rewards/margins": 46.738731384277344,
+      "rewards/rejected": -54.60127639770508,
+      "step": 980
+    },
+    {
+      "epoch": 0.7770800627943485,
+      "grad_norm": 18.103997714286827,
+      "learning_rate": 7.201594655002458e-08,
+      "logits/chosen": 5944.6259765625,
+      "logits/rejected": 5010.23876953125,
+      "logps/chosen": -238.925048828125,
+      "logps/rejected": -244.1151580810547,
+      "loss": -0.5534,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -13.030115127563477,
+      "rewards/margins": 37.01529312133789,
+      "rewards/rejected": -50.04541015625,
+      "step": 990
+    },
+    {
+      "epoch": 0.7849293563579278,
+      "grad_norm": 17.968333064385718,
+      "learning_rate": 6.727067196345099e-08,
+      "logits/chosen": 5641.294921875,
+      "logits/rejected": 4806.80517578125,
+      "logps/chosen": -224.1138458251953,
+      "logps/rejected": -217.52890014648438,
+      "loss": -0.5483,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -10.35799503326416,
+      "rewards/margins": 26.82565689086914,
+      "rewards/rejected": -37.18364715576172,
+      "step": 1000
+    },
+    {
+      "epoch": 0.792778649921507,
+      "grad_norm": 13.263741910622812,
+      "learning_rate": 6.26627103495786e-08,
+      "logits/chosen": 5823.0947265625,
+      "logits/rejected": 4895.5849609375,
+      "logps/chosen": -223.3077850341797,
+      "logps/rejected": -230.5642852783203,
+      "loss": -0.5494,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -8.598567008972168,
+      "rewards/margins": 30.532119750976562,
+      "rewards/rejected": -39.13068389892578,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8006279434850864,
+      "grad_norm": 14.14161334701853,
+      "learning_rate": 5.8195524386862374e-08,
+      "logits/chosen": 5912.64306640625,
+      "logits/rejected": 5297.43408203125,
+      "logps/chosen": -255.5826873779297,
+      "logps/rejected": -267.65789794921875,
+      "loss": -0.5487,
+      "rewards/accuracies": 0.8333333730697632,
+      "rewards/chosen": -7.4040656089782715,
+      "rewards/margins": 34.17313766479492,
+      "rewards/rejected": -41.57720184326172,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8084772370486656,
+      "grad_norm": 16.110829515167328,
+      "learning_rate": 5.38724709671092e-08,
+      "logits/chosen": 6308.998046875,
+      "logits/rejected": 5989.17822265625,
+      "logps/chosen": -242.4403839111328,
+      "logps/rejected": -275.2937927246094,
+      "loss": -0.5528,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -10.972010612487793,
+      "rewards/margins": 31.2025203704834,
+      "rewards/rejected": -42.17452621459961,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 19.509435425991782,
+      "learning_rate": 4.969679867292276e-08,
+      "logits/chosen": 5612.50244140625,
+      "logits/rejected": 5153.9169921875,
+      "logps/chosen": -233.4686279296875,
+      "logps/rejected": -257.07269287109375,
+      "loss": -0.5516,
+      "rewards/accuracies": 0.7000001072883606,
+      "rewards/chosen": -13.366943359375,
+      "rewards/margins": 34.52176284790039,
+      "rewards/rejected": -47.88870620727539,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 16.431746409803452,
+      "learning_rate": 4.5671645336537416e-08,
+      "logits/chosen": 5662.87255859375,
+      "logits/rejected": 5196.033203125,
+      "logps/chosen": -249.39706420898438,
+      "logps/rejected": -264.2225341796875,
+      "loss": -0.5558,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -11.916464805603027,
+      "rewards/margins": 36.51172637939453,
+      "rewards/rejected": -48.428192138671875,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8320251177394035,
+      "grad_norm": 21.652998761202152,
+      "learning_rate": 4.180003568187776e-08,
+      "logits/chosen": 6986.6953125,
+      "logits/rejected": 5531.6259765625,
+      "logps/chosen": -275.694091796875,
+      "logps/rejected": -260.778564453125,
+      "loss": -0.5439,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -14.706733703613281,
+      "rewards/margins": 26.032629013061523,
+      "rewards/rejected": -40.73936080932617,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8398744113029827,
+      "grad_norm": 14.876687749593671,
+      "learning_rate": 3.8084879051612144e-08,
+      "logits/chosen": 5824.328125,
+      "logits/rejected": 5373.7041015625,
+      "logps/chosen": -233.8295135498047,
+      "logps/rejected": -236.5215606689453,
+      "loss": -0.5511,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -8.586492538452148,
+      "rewards/margins": 34.77070617675781,
+      "rewards/rejected": -43.357200622558594,
+      "step": 1070
+    },
+    {
+      "epoch": 0.847723704866562,
+      "grad_norm": 16.725130244781578,
+      "learning_rate": 3.452896722091128e-08,
+      "logits/chosen": 6377.11328125,
+      "logits/rejected": 4972.22021484375,
+      "logps/chosen": -273.76922607421875,
+      "logps/rejected": -250.38369750976562,
+      "loss": -0.5561,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -7.199933052062988,
+      "rewards/margins": 42.20384216308594,
+      "rewards/rejected": -49.403770446777344,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8555729984301413,
+      "grad_norm": 14.877863636251977,
+      "learning_rate": 3.11349722995527e-08,
+      "logits/chosen": 6464.0947265625,
+      "logits/rejected": 4879.25830078125,
+      "logps/chosen": -240.05032348632812,
+      "logps/rejected": -255.6093292236328,
+      "loss": -0.5505,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -12.57571029663086,
+      "rewards/margins": 30.14911460876465,
+      "rewards/rejected": -42.724822998046875,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8634222919937206,
+      "grad_norm": 20.19569564301896,
+      "learning_rate": 2.7905444723949762e-08,
+      "logits/chosen": 6226.359375,
+      "logits/rejected": 5178.37890625,
+      "logps/chosen": -251.06362915039062,
+      "logps/rejected": -240.5138702392578,
+      "loss": -0.5505,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -12.527270317077637,
+      "rewards/margins": 38.48920440673828,
+      "rewards/rejected": -51.0164794921875,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8712715855572999,
+      "grad_norm": 17.825514771274925,
+      "learning_rate": 2.484281134061142e-08,
+      "logits/chosen": 6591.82666015625,
+      "logits/rejected": 5353.4365234375,
+      "logps/chosen": -276.72772216796875,
+      "logps/rejected": -268.7568359375,
+      "loss": -0.5523,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -12.114155769348145,
+      "rewards/margins": 34.37467956542969,
+      "rewards/rejected": -46.48883819580078,
+      "step": 1110
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 16.02405187464744,
+      "learning_rate": 2.194937358247506e-08,
+      "logits/chosen": 6450.017578125,
+      "logits/rejected": 5275.9541015625,
+      "logps/chosen": -259.4888610839844,
+      "logps/rejected": -264.9927673339844,
+      "loss": -0.5526,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -14.348428726196289,
+      "rewards/margins": 33.87355422973633,
+      "rewards/rejected": -48.22198486328125,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8869701726844584,
+      "grad_norm": 16.718921795503945,
+      "learning_rate": 1.9227305739481612e-08,
+      "logits/chosen": 5868.09326171875,
+      "logits/rejected": 4665.5556640625,
+      "logps/chosen": -243.3276824951172,
+      "logps/rejected": -224.7455291748047,
+      "loss": -0.5524,
+      "rewards/accuracies": 0.7416666150093079,
+      "rewards/chosen": -8.54565143585205,
+      "rewards/margins": 35.97431564331055,
+      "rewards/rejected": -44.51996612548828,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8948194662480377,
+      "grad_norm": 21.87301219927631,
+      "learning_rate": 1.6678653324693787e-08,
+      "logits/chosen": 6443.2421875,
+      "logits/rejected": 5277.41650390625,
+      "logps/chosen": -267.6515197753906,
+      "logps/rejected": -263.9855651855469,
+      "loss": -0.5556,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -10.030736923217773,
+      "rewards/margins": 33.14179992675781,
+      "rewards/rejected": -43.17253494262695,
+      "step": 1140
+    },
+    {
+      "epoch": 0.902668759811617,
+      "grad_norm": 16.394242263229533,
+      "learning_rate": 1.4305331537183384e-08,
+      "logits/chosen": 5703.8076171875,
+      "logits/rejected": 5282.501953125,
+      "logps/chosen": -237.505859375,
+      "logps/rejected": -260.38348388671875,
+      "loss": -0.5545,
+      "rewards/accuracies": 0.708333432674408,
+      "rewards/chosen": -10.52247142791748,
+      "rewards/margins": 30.373050689697266,
+      "rewards/rejected": -40.8955192565918,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9105180533751962,
+      "grad_norm": 15.137357364789535,
+      "learning_rate": 1.2109123822844653e-08,
+      "logits/chosen": 5874.21923828125,
+      "logits/rejected": 4698.57373046875,
+      "logps/chosen": -242.8210906982422,
+      "logps/rejected": -237.9269561767578,
+      "loss": -0.5498,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -14.264314651489258,
+      "rewards/margins": 27.72454261779785,
+      "rewards/rejected": -41.988861083984375,
+      "step": 1160
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 14.46432731958664,
+      "learning_rate": 1.0091680534213387e-08,
+      "logits/chosen": 6431.46875,
+      "logits/rejected": 6211.9443359375,
+      "logps/chosen": -255.26016235351562,
+      "logps/rejected": -287.64178466796875,
+      "loss": -0.5454,
+      "rewards/accuracies": 0.6833333969116211,
+      "rewards/chosen": -12.311790466308594,
+      "rewards/margins": 28.583049774169922,
+      "rewards/rejected": -40.89484405517578,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9262166405023547,
+      "grad_norm": 17.64924306448341,
+      "learning_rate": 8.254517690300944e-09,
+      "logits/chosen": 5668.1728515625,
+      "logits/rejected": 5178.52587890625,
+      "logps/chosen": -250.7957000732422,
+      "logps/rejected": -257.81732177734375,
+      "loss": -0.5488,
+      "rewards/accuracies": 0.7250000834465027,
+      "rewards/chosen": -10.84972095489502,
+      "rewards/margins": 30.14580726623535,
+      "rewards/rejected": -40.99553680419922,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9340659340659341,
+      "grad_norm": 18.427229973583398,
+      "learning_rate": 6.599015837372907e-09,
+      "logits/chosen": 6148.91015625,
+      "logits/rejected": 5400.935546875,
+      "logps/chosen": -267.8089904785156,
+      "logps/rejected": -266.39111328125,
+      "loss": -0.5519,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -18.923511505126953,
+      "rewards/margins": 30.315160751342773,
+      "rewards/rejected": -49.238670349121094,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9419152276295133,
+      "grad_norm": 15.198909725849877,
+      "learning_rate": 5.126419011529992e-09,
+      "logits/chosen": 6354.642578125,
+      "logits/rejected": 5444.1533203125,
+      "logps/chosen": -264.5579528808594,
+      "logps/rejected": -269.75518798828125,
+      "loss": -0.5561,
+      "rewards/accuracies": 0.8416666984558105,
+      "rewards/chosen": -8.896267890930176,
+      "rewards/margins": 42.1933479309082,
+      "rewards/rejected": -51.0896110534668,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9497645211930926,
+      "grad_norm": 17.684751446194035,
+      "learning_rate": 3.837833803870177e-09,
+      "logits/chosen": 5944.4462890625,
+      "logits/rejected": 5231.82958984375,
+      "logps/chosen": -252.0420379638672,
+      "logps/rejected": -267.1654968261719,
+      "loss": -0.551,
+      "rewards/accuracies": 0.7916667461395264,
+      "rewards/chosen": -11.856538772583008,
+      "rewards/margins": 37.107666015625,
+      "rewards/rejected": -48.96420669555664,
+      "step": 1210
+    },
+    {
+      "epoch": 0.957613814756672,
+      "grad_norm": 15.438763360340188,
+      "learning_rate": 2.734228528934679e-09,
+      "logits/chosen": 7407.5537109375,
+      "logits/rejected": 5488.259765625,
+      "logps/chosen": -311.3385925292969,
+      "logps/rejected": -292.863037109375,
+      "loss": -0.5477,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -14.570196151733398,
+      "rewards/margins": 33.09563064575195,
+      "rewards/rejected": -47.66582489013672,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9654631083202512,
+      "grad_norm": 14.94216025982471,
+      "learning_rate": 1.8164324970625645e-09,
+      "logits/chosen": 6597.4267578125,
+      "logits/rejected": 5241.8212890625,
+      "logps/chosen": -269.3259582519531,
+      "logps/rejected": -258.00634765625,
+      "loss": -0.5511,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -8.744241714477539,
+      "rewards/margins": 36.2653694152832,
+      "rewards/rejected": -45.009605407714844,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9733124018838305,
+      "grad_norm": 14.89107007034069,
+      "learning_rate": 1.0851353912008642e-09,
+      "logits/chosen": 5685.677734375,
+      "logits/rejected": 5243.69921875,
+      "logps/chosen": -246.015869140625,
+      "logps/rejected": -281.5025329589844,
+      "loss": -0.5539,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": -14.403498649597168,
+      "rewards/margins": 31.941186904907227,
+      "rewards/rejected": -46.34468460083008,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9811616954474097,
+      "grad_norm": 15.076764546390999,
+      "learning_rate": 5.408867486384471e-10,
+      "logits/chosen": 5798.7353515625,
+      "logits/rejected": 4921.08642578125,
+      "logps/chosen": -240.26687622070312,
+      "logps/rejected": -225.79238891601562,
+      "loss": -0.5486,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -9.958760261535645,
+      "rewards/margins": 26.4033203125,
+      "rewards/rejected": -36.362083435058594,
+      "step": 1250
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 21.445426738337094,
+      "learning_rate": 1.840955480532924e-10,
+      "logits/chosen": 5476.0166015625,
+      "logits/rejected": 5215.1123046875,
+      "logps/chosen": -244.2669219970703,
+      "logps/rejected": -257.24847412109375,
+      "loss": -0.5525,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -12.10632610321045,
+      "rewards/margins": 28.817041397094727,
+      "rewards/rejected": -40.923362731933594,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9968602825745683,
+      "grad_norm": 15.790140219517752,
+      "learning_rate": 1.502990218302247e-11,
+      "logits/chosen": 5753.83544921875,
+      "logits/rejected": 4702.4267578125,
+      "logps/chosen": -235.7917938232422,
+      "logps/rejected": -232.51882934570312,
+      "loss": -0.5564,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -11.317852020263672,
+      "rewards/margins": 34.89674377441406,
+      "rewards/rejected": -46.214599609375,
+      "step": 1270
+    },
+    {
+      "epoch": 1.0,
+      "step": 1274,
+      "total_flos": 0.0,
+      "train_loss": -0.5441001898826946,
+      "train_runtime": 14755.3414,
+      "train_samples_per_second": 4.143,
+      "train_steps_per_second": 0.086
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1274,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}