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_BrierAll-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_BrierAll-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 2.2.2+cu118
+- Datasets 2.19.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.4838377035206865,
+    "train_runtime": 15889.6187,
+    "train_samples": 61135,
+    "train_samples_per_second": 3.847,
+    "train_steps_per_second": 0.08
+}

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 sha256:9c07b3ace97bbcebc96ea041de6497bef1ff6d1167663bbfd5b78b3012cca8c8
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b50ffd0340ca0e8fe67befa012727394d4f5886e03e43281b6aa7d72731be4d1
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6b998e0ac21151786b6c58dda60de2ffdf3462a2c4383a700b09b691006f00
+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": 0.4838377035206865,
+    "train_runtime": 15889.6187,
+    "train_samples": 61135,
+    "train_samples_per_second": 3.847,
+    "train_steps_per_second": 0.08
+}

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": 3.0487772677725773,
+      "learning_rate": 3.90625e-09,
+      "logits/chosen": 5914.86328125,
+      "logits/rejected": 2785.05078125,
+      "logps/chosen": -212.39956665039062,
+      "logps/rejected": -98.58319854736328,
+      "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": 3.0053521826261167,
+      "learning_rate": 3.9062499999999997e-08,
+      "logits/chosen": 4973.92333984375,
+      "logits/rejected": 4328.39306640625,
+      "logps/chosen": -204.2337646484375,
+      "logps/rejected": -179.74032592773438,
+      "loss": 0.5,
+      "rewards/accuracies": 0.45370373129844666,
+      "rewards/chosen": -0.026329733431339264,
+      "rewards/margins": 0.02287517488002777,
+      "rewards/rejected": -0.049204908311367035,
+      "step": 10
+    },
+    {
+      "epoch": 0.015698587127158554,
+      "grad_norm": 3.0978467775902003,
+      "learning_rate": 7.812499999999999e-08,
+      "logits/chosen": 6084.19091796875,
+      "logits/rejected": 4834.38525390625,
+      "logps/chosen": -217.27499389648438,
+      "logps/rejected": -196.74400329589844,
+      "loss": 0.5,
+      "rewards/accuracies": 0.4583333432674408,
+      "rewards/chosen": -0.08536674082279205,
+      "rewards/margins": -0.07421146333217621,
+      "rewards/rejected": -0.011155286803841591,
+      "step": 20
+    },
+    {
+      "epoch": 0.023547880690737835,
+      "grad_norm": 2.7446834255139536,
+      "learning_rate": 1.1718749999999999e-07,
+      "logits/chosen": 6084.2724609375,
+      "logits/rejected": 5104.916015625,
+      "logps/chosen": -250.5588836669922,
+      "logps/rejected": -209.36581420898438,
+      "loss": 0.4999,
+      "rewards/accuracies": 0.5666667222976685,
+      "rewards/chosen": 0.027410000562667847,
+      "rewards/margins": 0.05924432352185249,
+      "rewards/rejected": -0.031834326684474945,
+      "step": 30
+    },
+    {
+      "epoch": 0.03139717425431711,
+      "grad_norm": 2.843553303611542,
+      "learning_rate": 1.5624999999999999e-07,
+      "logits/chosen": 5311.85302734375,
+      "logits/rejected": 4347.0205078125,
+      "logps/chosen": -212.00399780273438,
+      "logps/rejected": -181.74400329589844,
+      "loss": 0.4998,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.08414590358734131,
+      "rewards/margins": 0.15114834904670715,
+      "rewards/rejected": -0.06700245290994644,
+      "step": 40
+    },
+    {
+      "epoch": 0.03924646781789639,
+      "grad_norm": 2.8825607029859888,
+      "learning_rate": 1.9531249999999998e-07,
+      "logits/chosen": 6424.96923828125,
+      "logits/rejected": 5042.35986328125,
+      "logps/chosen": -265.3002014160156,
+      "logps/rejected": -206.8275909423828,
+      "loss": 0.4996,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.3166608512401581,
+      "rewards/margins": 0.4250132441520691,
+      "rewards/rejected": -0.1083524227142334,
+      "step": 50
+    },
+    {
+      "epoch": 0.04709576138147567,
+      "grad_norm": 2.778870633582961,
+      "learning_rate": 2.3437499999999998e-07,
+      "logits/chosen": 5484.5029296875,
+      "logits/rejected": 4560.0517578125,
+      "logps/chosen": -213.75253295898438,
+      "logps/rejected": -209.1453857421875,
+      "loss": 0.4994,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 0.22474229335784912,
+      "rewards/margins": 0.5068433284759521,
+      "rewards/rejected": -0.2821010947227478,
+      "step": 60
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 2.682504764489562,
+      "learning_rate": 2.734375e-07,
+      "logits/chosen": 5194.5400390625,
+      "logits/rejected": 4918.72998046875,
+      "logps/chosen": -178.332763671875,
+      "logps/rejected": -177.39456176757812,
+      "loss": 0.499,
+      "rewards/accuracies": 0.6750000715255737,
+      "rewards/chosen": 0.16802605986595154,
+      "rewards/margins": 0.7994251251220703,
+      "rewards/rejected": -0.6313990354537964,
+      "step": 70
+    },
+    {
+      "epoch": 0.06279434850863422,
+      "grad_norm": 2.8218819506262163,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 5774.5458984375,
+      "logits/rejected": 5270.11328125,
+      "logps/chosen": -196.78280639648438,
+      "logps/rejected": -182.97372436523438,
+      "loss": 0.498,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.20524080097675323,
+      "rewards/margins": 1.2131010293960571,
+      "rewards/rejected": -1.418341875076294,
+      "step": 80
+    },
+    {
+      "epoch": 0.0706436420722135,
+      "grad_norm": 3.248309171746226,
+      "learning_rate": 3.5156249999999997e-07,
+      "logits/chosen": 6040.18896484375,
+      "logits/rejected": 5181.7353515625,
+      "logps/chosen": -220.0659942626953,
+      "logps/rejected": -190.46095275878906,
+      "loss": 0.4961,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -1.2045572996139526,
+      "rewards/margins": 4.808753490447998,
+      "rewards/rejected": -6.01331090927124,
+      "step": 90
+    },
+    {
+      "epoch": 0.07849293563579278,
+      "grad_norm": 3.554254071863816,
+      "learning_rate": 3.9062499999999997e-07,
+      "logits/chosen": 5967.5380859375,
+      "logits/rejected": 5745.78662109375,
+      "logps/chosen": -213.9711151123047,
+      "logps/rejected": -208.7987823486328,
+      "loss": 0.4967,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -3.739614486694336,
+      "rewards/margins": 5.641757965087891,
+      "rewards/rejected": -9.381372451782227,
+      "step": 100
+    },
+    {
+      "epoch": 0.08634222919937205,
+      "grad_norm": 3.031810586718979,
+      "learning_rate": 4.2968749999999996e-07,
+      "logits/chosen": 6471.2333984375,
+      "logits/rejected": 5290.38720703125,
+      "logps/chosen": -188.45823669433594,
+      "logps/rejected": -190.59783935546875,
+      "loss": 0.4944,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -5.357982158660889,
+      "rewards/margins": 6.315234661102295,
+      "rewards/rejected": -11.6732177734375,
+      "step": 110
+    },
+    {
+      "epoch": 0.09419152276295134,
+      "grad_norm": 4.2099755788258655,
+      "learning_rate": 4.6874999999999996e-07,
+      "logits/chosen": 6397.25732421875,
+      "logits/rejected": 5324.435546875,
+      "logps/chosen": -210.238037109375,
+      "logps/rejected": -212.63900756835938,
+      "loss": 0.4933,
+      "rewards/accuracies": 0.6583333611488342,
+      "rewards/chosen": -7.363883018493652,
+      "rewards/margins": 7.125211238861084,
+      "rewards/rejected": -14.489092826843262,
+      "step": 120
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 3.1665933110373725,
+      "learning_rate": 4.999962424962166e-07,
+      "logits/chosen": 6331.97216796875,
+      "logits/rejected": 5862.5107421875,
+      "logps/chosen": -215.6492462158203,
+      "logps/rejected": -212.6134796142578,
+      "loss": 0.4923,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -5.834831714630127,
+      "rewards/margins": 9.114367485046387,
+      "rewards/rejected": -14.949200630187988,
+      "step": 130
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 3.7689016805629443,
+      "learning_rate": 4.998647417232375e-07,
+      "logits/chosen": 6194.1015625,
+      "logits/rejected": 5455.68408203125,
+      "logps/chosen": -194.98805236816406,
+      "logps/rejected": -196.2983856201172,
+      "loss": 0.4918,
+      "rewards/accuracies": 0.6250000596046448,
+      "rewards/chosen": -9.310918807983398,
+      "rewards/margins": 9.410451889038086,
+      "rewards/rejected": -18.721370697021484,
+      "step": 140
+    },
+    {
+      "epoch": 0.11773940345368916,
+      "grad_norm": 4.43082355946498,
+      "learning_rate": 4.995454786965036e-07,
+      "logits/chosen": 6372.63232421875,
+      "logits/rejected": 5326.8037109375,
+      "logps/chosen": -209.4663543701172,
+      "logps/rejected": -191.9363555908203,
+      "loss": 0.4903,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -7.847425937652588,
+      "rewards/margins": 11.783364295959473,
+      "rewards/rejected": -19.630788803100586,
+      "step": 150
+    },
+    {
+      "epoch": 0.12558869701726844,
+      "grad_norm": 3.480825908331641,
+      "learning_rate": 4.990386933279972e-07,
+      "logits/chosen": 6321.26220703125,
+      "logits/rejected": 5649.68896484375,
+      "logps/chosen": -207.1846160888672,
+      "logps/rejected": -218.85598754882812,
+      "loss": 0.49,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -9.681838989257812,
+      "rewards/margins": 12.111849784851074,
+      "rewards/rejected": -21.793689727783203,
+      "step": 160
+    },
+    {
+      "epoch": 0.13343799058084774,
+      "grad_norm": 3.106180556431054,
+      "learning_rate": 4.983447664444096e-07,
+      "logits/chosen": 6514.87060546875,
+      "logits/rejected": 5810.04541015625,
+      "logps/chosen": -219.171142578125,
+      "logps/rejected": -215.4300994873047,
+      "loss": 0.4906,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -9.55972671508789,
+      "rewards/margins": 9.543268203735352,
+      "rewards/rejected": -19.10299301147461,
+      "step": 170
+    },
+    {
+      "epoch": 0.141287284144427,
+      "grad_norm": 3.643487198805099,
+      "learning_rate": 4.97464219500968e-07,
+      "logits/chosen": 5706.86279296875,
+      "logits/rejected": 4987.03857421875,
+      "logps/chosen": -197.81028747558594,
+      "logps/rejected": -198.56837463378906,
+      "loss": 0.4893,
+      "rewards/accuracies": 0.6583333015441895,
+      "rewards/chosen": -9.248052597045898,
+      "rewards/margins": 11.146056175231934,
+      "rewards/rejected": -20.39410972595215,
+      "step": 180
+    },
+    {
+      "epoch": 0.14913657770800628,
+      "grad_norm": 3.8856644246575103,
+      "learning_rate": 4.963977141895843e-07,
+      "logits/chosen": 5854.3115234375,
+      "logits/rejected": 5032.4169921875,
+      "logps/chosen": -213.3368377685547,
+      "logps/rejected": -223.55172729492188,
+      "loss": 0.4872,
+      "rewards/accuracies": 0.7416667342185974,
+      "rewards/chosen": -9.566925048828125,
+      "rewards/margins": 22.772855758666992,
+      "rewards/rejected": -32.33978271484375,
+      "step": 190
+    },
+    {
+      "epoch": 0.15698587127158556,
+      "grad_norm": 4.297205531104238,
+      "learning_rate": 4.951460519416227e-07,
+      "logits/chosen": 5780.6923828125,
+      "logits/rejected": 5346.49755859375,
+      "logps/chosen": -191.6383056640625,
+      "logps/rejected": -223.6271514892578,
+      "loss": 0.4866,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -9.101288795471191,
+      "rewards/margins": 17.816524505615234,
+      "rewards/rejected": -26.91781234741211,
+      "step": 200
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 4.292179021789101,
+      "learning_rate": 4.937101733256606e-07,
+      "logits/chosen": 5224.7744140625,
+      "logits/rejected": 4661.73486328125,
+      "logps/chosen": -165.87432861328125,
+      "logps/rejected": -186.35812377929688,
+      "loss": 0.4863,
+      "rewards/accuracies": 0.6833333969116211,
+      "rewards/chosen": -11.944615364074707,
+      "rewards/margins": 17.197933197021484,
+      "rewards/rejected": -29.142547607421875,
+      "step": 210
+    },
+    {
+      "epoch": 0.1726844583987441,
+      "grad_norm": 6.626714055788658,
+      "learning_rate": 4.920911573406924e-07,
+      "logits/chosen": 6370.0927734375,
+      "logits/rejected": 5428.90673828125,
+      "logps/chosen": -205.94155883789062,
+      "logps/rejected": -190.01119995117188,
+      "loss": 0.4867,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -9.667407035827637,
+      "rewards/margins": 16.392742156982422,
+      "rewards/rejected": -26.06014633178711,
+      "step": 220
+    },
+    {
+      "epoch": 0.18053375196232338,
+      "grad_norm": 3.7173875214230696,
+      "learning_rate": 4.902902206053098e-07,
+      "logits/chosen": 5841.6572265625,
+      "logits/rejected": 5277.27880859375,
+      "logps/chosen": -201.20584106445312,
+      "logps/rejected": -213.4195098876953,
+      "loss": 0.488,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -13.862586975097656,
+      "rewards/margins": 19.78961181640625,
+      "rewards/rejected": -33.652198791503906,
+      "step": 230
+    },
+    {
+      "epoch": 0.18838304552590268,
+      "grad_norm": 3.9111196709731266,
+      "learning_rate": 4.883087164434672e-07,
+      "logits/chosen": 5335.8388671875,
+      "logits/rejected": 4271.4931640625,
+      "logps/chosen": -176.08363342285156,
+      "logps/rejected": -179.86932373046875,
+      "loss": 0.4862,
+      "rewards/accuracies": 0.73333340883255,
+      "rewards/chosen": -8.456828117370605,
+      "rewards/margins": 16.693925857543945,
+      "rewards/rejected": -25.150753021240234,
+      "step": 240
+    },
+    {
+      "epoch": 0.19623233908948196,
+      "grad_norm": 4.261331874415065,
+      "learning_rate": 4.861481338675183e-07,
+      "logits/chosen": 6306.83984375,
+      "logits/rejected": 5615.685546875,
+      "logps/chosen": -178.5889434814453,
+      "logps/rejected": -217.28970336914062,
+      "loss": 0.4868,
+      "rewards/accuracies": 0.716666579246521,
+      "rewards/chosen": -11.434499740600586,
+      "rewards/margins": 21.358827590942383,
+      "rewards/rejected": -32.79332733154297,
+      "step": 250
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 4.425252839892343,
+      "learning_rate": 4.838100964592904e-07,
+      "logits/chosen": 6351.7236328125,
+      "logits/rejected": 5144.9755859375,
+      "logps/chosen": -210.78707885742188,
+      "logps/rejected": -193.6743621826172,
+      "loss": 0.4898,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -11.06749153137207,
+      "rewards/margins": 16.35895538330078,
+      "rewards/rejected": -27.426443099975586,
+      "step": 260
+    },
+    {
+      "epoch": 0.2119309262166405,
+      "grad_norm": 4.760542059577574,
+      "learning_rate": 4.812963611500339e-07,
+      "logits/chosen": 6243.24072265625,
+      "logits/rejected": 6046.0244140625,
+      "logps/chosen": -206.00430297851562,
+      "logps/rejected": -215.68295288085938,
+      "loss": 0.4822,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -9.247629165649414,
+      "rewards/margins": 17.734172821044922,
+      "rewards/rejected": -26.981800079345703,
+      "step": 270
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 4.753135680405862,
+      "learning_rate": 4.786088169001671e-07,
+      "logits/chosen": 5385.2890625,
+      "logits/rejected": 4686.9140625,
+      "logps/chosen": -173.31578063964844,
+      "logps/rejected": -209.2408905029297,
+      "loss": 0.4853,
+      "rewards/accuracies": 0.7666667699813843,
+      "rewards/chosen": -10.257834434509277,
+      "rewards/margins": 29.655181884765625,
+      "rewards/rejected": -39.91301727294922,
+      "step": 280
+    },
+    {
+      "epoch": 0.22762951334379905,
+      "grad_norm": 5.308144756301395,
+      "learning_rate": 4.7574948327980567e-07,
+      "logits/chosen": 7468.97119140625,
+      "logits/rejected": 5543.74853515625,
+      "logps/chosen": -245.2371063232422,
+      "logps/rejected": -216.72592163085938,
+      "loss": 0.4834,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -8.164133071899414,
+      "rewards/margins": 26.039669036865234,
+      "rewards/rejected": -34.20380401611328,
+      "step": 290
+    },
+    {
+      "epoch": 0.23547880690737832,
+      "grad_norm": 5.486434558365384,
+      "learning_rate": 4.727205089511466e-07,
+      "logits/chosen": 5443.1787109375,
+      "logits/rejected": 5416.29296875,
+      "logps/chosen": -179.67483520507812,
+      "logps/rejected": -203.97935485839844,
+      "loss": 0.4848,
+      "rewards/accuracies": 0.6750000715255737,
+      "rewards/chosen": -12.184015274047852,
+      "rewards/margins": 21.572368621826172,
+      "rewards/rejected": -33.756385803222656,
+      "step": 300
+    },
+    {
+      "epoch": 0.24332810047095763,
+      "grad_norm": 3.781388272504065,
+      "learning_rate": 4.6952417005384247e-07,
+      "logits/chosen": 6094.5146484375,
+      "logits/rejected": 5434.48388671875,
+      "logps/chosen": -186.70101928710938,
+      "logps/rejected": -201.45565795898438,
+      "loss": 0.4858,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -9.13051986694336,
+      "rewards/margins": 16.87561798095703,
+      "rewards/rejected": -26.00613784790039,
+      "step": 310
+    },
+    {
+      "epoch": 0.25117739403453687,
+      "grad_norm": 5.057187022551635,
+      "learning_rate": 4.661628684945851e-07,
+      "logits/chosen": 6113.8173828125,
+      "logits/rejected": 5304.43896484375,
+      "logps/chosen": -209.27749633789062,
+      "logps/rejected": -233.53720092773438,
+      "loss": 0.485,
+      "rewards/accuracies": 0.6833332777023315,
+      "rewards/chosen": -8.161227226257324,
+      "rewards/margins": 23.318111419677734,
+      "rewards/rejected": -31.47933578491211,
+      "step": 320
+    },
+    {
+      "epoch": 0.25902668759811615,
+      "grad_norm": 6.798726121505508,
+      "learning_rate": 4.626391301421782e-07,
+      "logits/chosen": 5900.6689453125,
+      "logits/rejected": 5375.3330078125,
+      "logps/chosen": -206.8414306640625,
+      "logps/rejected": -206.7434844970703,
+      "loss": 0.4896,
+      "rewards/accuracies": 0.6916666626930237,
+      "rewards/chosen": -12.424559593200684,
+      "rewards/margins": 16.98659896850586,
+      "rewards/rejected": -29.41115951538086,
+      "step": 330
+    },
+    {
+      "epoch": 0.2668759811616955,
+      "grad_norm": 5.700700349878508,
+      "learning_rate": 4.5895560292945996e-07,
+      "logits/chosen": 6139.4365234375,
+      "logits/rejected": 6274.908203125,
+      "logps/chosen": -201.94586181640625,
+      "logps/rejected": -249.42214965820312,
+      "loss": 0.4865,
+      "rewards/accuracies": 0.7083333134651184,
+      "rewards/chosen": -8.077656745910645,
+      "rewards/margins": 20.984493255615234,
+      "rewards/rejected": -29.062152862548828,
+      "step": 340
+    },
+    {
+      "epoch": 0.27472527472527475,
+      "grad_norm": 5.977413665609151,
+      "learning_rate": 4.5511505486349865e-07,
+      "logits/chosen": 6463.08056640625,
+      "logits/rejected": 5862.45263671875,
+      "logps/chosen": -203.75619506835938,
+      "logps/rejected": -246.5824737548828,
+      "loss": 0.4814,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -8.89292049407959,
+      "rewards/margins": 30.91029930114746,
+      "rewards/rejected": -39.80322265625,
+      "step": 350
+    },
+    {
+      "epoch": 0.282574568288854,
+      "grad_norm": 4.373341515724122,
+      "learning_rate": 4.5112037194555876e-07,
+      "logits/chosen": 5958.3837890625,
+      "logits/rejected": 5866.4345703125,
+      "logps/chosen": -193.25698852539062,
+      "logps/rejected": -245.3924102783203,
+      "loss": 0.4862,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -15.391229629516602,
+      "rewards/margins": 30.65999984741211,
+      "rewards/rejected": -46.051231384277344,
+      "step": 360
+    },
+    {
+      "epoch": 0.2904238618524333,
+      "grad_norm": 4.757929648406688,
+      "learning_rate": 4.4697455600239863e-07,
+      "logits/chosen": 5432.66650390625,
+      "logits/rejected": 5125.18310546875,
+      "logps/chosen": -194.47439575195312,
+      "logps/rejected": -199.04013061523438,
+      "loss": 0.4874,
+      "rewards/accuracies": 0.6916666626930237,
+      "rewards/chosen": -10.048974990844727,
+      "rewards/margins": 20.923362731933594,
+      "rewards/rejected": -30.972335815429688,
+      "step": 370
+    },
+    {
+      "epoch": 0.29827315541601257,
+      "grad_norm": 5.665821177145355,
+      "learning_rate": 4.426807224305315e-07,
+      "logits/chosen": 6492.359375,
+      "logits/rejected": 5391.41650390625,
+      "logps/chosen": -236.5659942626953,
+      "logps/rejected": -214.6392364501953,
+      "loss": 0.484,
+      "rewards/accuracies": 0.7416667342185974,
+      "rewards/chosen": -8.198770523071289,
+      "rewards/margins": 23.478113174438477,
+      "rewards/rejected": -31.6768856048584,
+      "step": 380
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 10.143608229715067,
+      "learning_rate": 4.3824209785514326e-07,
+      "logits/chosen": 6633.6015625,
+      "logits/rejected": 5094.759765625,
+      "logps/chosen": -223.7018585205078,
+      "logps/rejected": -224.4058380126953,
+      "loss": 0.4807,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -8.22799301147461,
+      "rewards/margins": 36.34944534301758,
+      "rewards/rejected": -44.57743453979492,
+      "step": 390
+    },
+    {
+      "epoch": 0.3139717425431711,
+      "grad_norm": 4.292732523589074,
+      "learning_rate": 4.3366201770542687e-07,
+      "logits/chosen": 5725.72021484375,
+      "logits/rejected": 5617.19091796875,
+      "logps/chosen": -202.0982666015625,
+      "logps/rejected": -226.9371337890625,
+      "loss": 0.4873,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -11.27686882019043,
+      "rewards/margins": 26.9205379486084,
+      "rewards/rejected": -38.197410583496094,
+      "step": 400
+    },
+    {
+      "epoch": 0.3218210361067504,
+      "grad_norm": 6.392172730105889,
+      "learning_rate": 4.2894392370815567e-07,
+      "logits/chosen": 6202.8642578125,
+      "logits/rejected": 5540.9638671875,
+      "logps/chosen": -224.3190155029297,
+      "logps/rejected": -255.00234985351562,
+      "loss": 0.4775,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -11.845643997192383,
+      "rewards/margins": 34.68632507324219,
+      "rewards/rejected": -46.53197479248047,
+      "step": 410
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 7.029606333596596,
+      "learning_rate": 4.2409136130137845e-07,
+      "logits/chosen": 5864.06591796875,
+      "logits/rejected": 5320.2666015625,
+      "logps/chosen": -218.0572509765625,
+      "logps/rejected": -226.93960571289062,
+      "loss": 0.4831,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -14.010615348815918,
+      "rewards/margins": 31.634838104248047,
+      "rewards/rejected": -45.64545440673828,
+      "step": 420
+    },
+    {
+      "epoch": 0.33751962323390894,
+      "grad_norm": 5.156247112545232,
+      "learning_rate": 4.1910797697018017e-07,
+      "logits/chosen": 5653.123046875,
+      "logits/rejected": 4731.49755859375,
+      "logps/chosen": -190.7956085205078,
+      "logps/rejected": -205.7550048828125,
+      "loss": 0.4809,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -11.055082321166992,
+      "rewards/margins": 33.43699264526367,
+      "rewards/rejected": -44.4920768737793,
+      "step": 430
+    },
+    {
+      "epoch": 0.3453689167974882,
+      "grad_norm": 6.884631103602188,
+      "learning_rate": 4.1399751550651084e-07,
+      "logits/chosen": 5994.6748046875,
+      "logits/rejected": 5934.1728515625,
+      "logps/chosen": -194.4263916015625,
+      "logps/rejected": -232.75375366210938,
+      "loss": 0.4814,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -12.037619590759277,
+      "rewards/margins": 29.080547332763672,
+      "rewards/rejected": -41.1181640625,
+      "step": 440
+    },
+    {
+      "epoch": 0.3532182103610675,
+      "grad_norm": 5.22444942291216,
+      "learning_rate": 4.087638171951401e-07,
+      "logits/chosen": 6903.0205078125,
+      "logits/rejected": 5000.890625,
+      "logps/chosen": -216.89071655273438,
+      "logps/rejected": -208.60604858398438,
+      "loss": 0.4843,
+      "rewards/accuracies": 0.7499999403953552,
+      "rewards/chosen": -8.136539459228516,
+      "rewards/margins": 37.45273971557617,
+      "rewards/rejected": -45.58927536010742,
+      "step": 450
+    },
+    {
+      "epoch": 0.36106750392464676,
+      "grad_norm": 4.166107946627831,
+      "learning_rate": 4.034108149278543e-07,
+      "logits/chosen": 7097.2255859375,
+      "logits/rejected": 5557.1552734375,
+      "logps/chosen": -261.8773498535156,
+      "logps/rejected": -225.53298950195312,
+      "loss": 0.4846,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -11.391783714294434,
+      "rewards/margins": 24.004859924316406,
+      "rewards/rejected": -35.396644592285156,
+      "step": 460
+    },
+    {
+      "epoch": 0.36891679748822603,
+      "grad_norm": 6.4728785883394115,
+      "learning_rate": 3.979425312480629e-07,
+      "logits/chosen": 6111.62890625,
+      "logits/rejected": 5374.3291015625,
+      "logps/chosen": -224.78897094726562,
+      "logps/rejected": -242.69113159179688,
+      "loss": 0.4824,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -12.585268020629883,
+      "rewards/margins": 27.602148056030273,
+      "rewards/rejected": -40.18741226196289,
+      "step": 470
+    },
+    {
+      "epoch": 0.37676609105180536,
+      "grad_norm": 5.3655573665549205,
+      "learning_rate": 3.923630753280357e-07,
+      "logits/chosen": 6582.39990234375,
+      "logits/rejected": 5717.3642578125,
+      "logps/chosen": -219.0083465576172,
+      "logps/rejected": -220.59555053710938,
+      "loss": 0.4817,
+      "rewards/accuracies": 0.7916667461395264,
+      "rewards/chosen": -11.603225708007812,
+      "rewards/margins": 34.595619201660156,
+      "rewards/rejected": -46.1988410949707,
+      "step": 480
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 5.979735399161116,
+      "learning_rate": 3.866766398810424e-07,
+      "logits/chosen": 6178.900390625,
+      "logits/rejected": 5935.67626953125,
+      "logps/chosen": -181.1698760986328,
+      "logps/rejected": -238.9916534423828,
+      "loss": 0.4775,
+      "rewards/accuracies": 0.8083332777023315,
+      "rewards/chosen": -4.562686920166016,
+      "rewards/margins": 32.35731887817383,
+      "rewards/rejected": -36.920005798339844,
+      "step": 490
+    },
+    {
+      "epoch": 0.3924646781789639,
+      "grad_norm": 10.290243596769058,
+      "learning_rate": 3.8088749801071496e-07,
+      "logits/chosen": 6733.89990234375,
+      "logits/rejected": 5217.791015625,
+      "logps/chosen": -243.348388671875,
+      "logps/rejected": -263.6581115722656,
+      "loss": 0.4843,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -21.35295867919922,
+      "rewards/margins": 39.74835968017578,
+      "rewards/rejected": -61.101318359375,
+      "step": 500
+    },
+    {
+      "epoch": 0.4003139717425432,
+      "grad_norm": 5.406771505983375,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 5354.39697265625,
+      "logits/rejected": 4763.21044921875,
+      "logps/chosen": -198.2074737548828,
+      "logps/rejected": -207.1690673828125,
+      "loss": 0.4824,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -8.783690452575684,
+      "rewards/margins": 32.053260803222656,
+      "rewards/rejected": -40.836944580078125,
+      "step": 510
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 3.9154423666136626,
+      "learning_rate": 3.6901857004211443e-07,
+      "logits/chosen": 5683.8447265625,
+      "logits/rejected": 5304.09033203125,
+      "logps/chosen": -210.19241333007812,
+      "logps/rejected": -231.1099090576172,
+      "loss": 0.4884,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -11.772139549255371,
+      "rewards/margins": 23.49697494506836,
+      "rewards/rejected": -35.26911926269531,
+      "step": 520
+    },
+    {
+      "epoch": 0.41601255886970173,
+      "grad_norm": 5.038579766803527,
+      "learning_rate": 3.6294770291596076e-07,
+      "logits/chosen": 6436.02587890625,
+      "logits/rejected": 5317.28369140625,
+      "logps/chosen": -220.25057983398438,
+      "logps/rejected": -229.13784790039062,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": -7.315767765045166,
+      "rewards/margins": 23.054981231689453,
+      "rewards/rejected": -30.37074851989746,
+      "step": 530
+    },
+    {
+      "epoch": 0.423861852433281,
+      "grad_norm": 9.177958827560293,
+      "learning_rate": 3.5679196060850034e-07,
+      "logits/chosen": 6133.5283203125,
+      "logits/rejected": 5512.38818359375,
+      "logps/chosen": -224.00009155273438,
+      "logps/rejected": -239.9444122314453,
+      "loss": 0.484,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -13.195943832397461,
+      "rewards/margins": 38.481021881103516,
+      "rewards/rejected": -51.676963806152344,
+      "step": 540
+    },
+    {
+      "epoch": 0.4317111459968603,
+      "grad_norm": 5.4423546958299385,
+      "learning_rate": 3.505559688866229e-07,
+      "logits/chosen": 5929.5986328125,
+      "logits/rejected": 5545.6748046875,
+      "logps/chosen": -226.8612823486328,
+      "logps/rejected": -273.16229248046875,
+      "loss": 0.4784,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -12.048417091369629,
+      "rewards/margins": 36.062232971191406,
+      "rewards/rejected": -48.110652923583984,
+      "step": 550
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 4.766412998974481,
+      "learning_rate": 3.4424441382108826e-07,
+      "logits/chosen": 5972.25830078125,
+      "logits/rejected": 5610.7490234375,
+      "logps/chosen": -217.2675018310547,
+      "logps/rejected": -234.3104705810547,
+      "loss": 0.4871,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -13.991231918334961,
+      "rewards/margins": 27.081674575805664,
+      "rewards/rejected": -41.07290267944336,
+      "step": 560
+    },
+    {
+      "epoch": 0.4474097331240188,
+      "grad_norm": 6.338785824551311,
+      "learning_rate": 3.378620382651523e-07,
+      "logits/chosen": 6286.69287109375,
+      "logits/rejected": 5813.5283203125,
+      "logps/chosen": -255.1618194580078,
+      "logps/rejected": -267.93878173828125,
+      "loss": 0.4808,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -12.230340957641602,
+      "rewards/margins": 31.982650756835938,
+      "rewards/rejected": -44.212989807128906,
+      "step": 570
+    },
+    {
+      "epoch": 0.4552590266875981,
+      "grad_norm": 7.016140317833379,
+      "learning_rate": 3.314136382905234e-07,
+      "logits/chosen": 6247.73046875,
+      "logits/rejected": 5671.7021484375,
+      "logps/chosen": -222.32693481445312,
+      "logps/rejected": -259.5238952636719,
+      "loss": 0.4828,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -9.925975799560547,
+      "rewards/margins": 36.31413269042969,
+      "rewards/rejected": -46.24010467529297,
+      "step": 580
+    },
+    {
+      "epoch": 0.4631083202511774,
+      "grad_norm": 10.530000697305884,
+      "learning_rate": 3.249040595833274e-07,
+      "logits/chosen": 6807.6484375,
+      "logits/rejected": 5773.490234375,
+      "logps/chosen": -242.41659545898438,
+      "logps/rejected": -225.3022003173828,
+      "loss": 0.4788,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -10.745205879211426,
+      "rewards/margins": 35.73249435424805,
+      "rewards/rejected": -46.47770309448242,
+      "step": 590
+    },
+    {
+      "epoch": 0.47095761381475665,
+      "grad_norm": 8.512339938567651,
+      "learning_rate": 3.1833819380279023e-07,
+      "logits/chosen": 6445.0234375,
+      "logits/rejected": 5518.9345703125,
+      "logps/chosen": -186.99856567382812,
+      "logps/rejected": -234.09817504882812,
+      "loss": 0.4785,
+      "rewards/accuracies": 0.8166667222976685,
+      "rewards/chosen": -9.450994491577148,
+      "rewards/margins": 34.949501037597656,
+      "rewards/rejected": -44.40049743652344,
+      "step": 600
+    },
+    {
+      "epoch": 0.478806907378336,
+      "grad_norm": 4.8733837949422885,
+      "learning_rate": 3.11720974905373e-07,
+      "logits/chosen": 6186.08447265625,
+      "logits/rejected": 5429.20361328125,
+      "logps/chosen": -218.30288696289062,
+      "logps/rejected": -232.8191680908203,
+      "loss": 0.4793,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -12.169063568115234,
+      "rewards/margins": 35.24351119995117,
+      "rewards/rejected": -47.412574768066406,
+      "step": 610
+    },
+    {
+      "epoch": 0.48665620094191525,
+      "grad_norm": 5.136229399526287,
+      "learning_rate": 3.0505737543712275e-07,
+      "logits/chosen": 5280.85546875,
+      "logits/rejected": 4370.572265625,
+      "logps/chosen": -196.75811767578125,
+      "logps/rejected": -205.48971557617188,
+      "loss": 0.4806,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -12.993181228637695,
+      "rewards/margins": 31.400897979736328,
+      "rewards/rejected": -44.394081115722656,
+      "step": 620
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 6.5054877538720985,
+      "learning_rate": 2.9835240279702513e-07,
+      "logits/chosen": 6880.61083984375,
+      "logits/rejected": 5913.2353515625,
+      "logps/chosen": -251.8698272705078,
+      "logps/rejected": -250.5375518798828,
+      "loss": 0.4787,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -9.037474632263184,
+      "rewards/margins": 47.23527526855469,
+      "rewards/rejected": -56.27274703979492,
+      "step": 630
+    },
+    {
+      "epoch": 0.5023547880690737,
+      "grad_norm": 8.979595260533317,
+      "learning_rate": 2.9161109547416667e-07,
+      "logits/chosen": 6547.708984375,
+      "logits/rejected": 5625.1787109375,
+      "logps/chosen": -224.85488891601562,
+      "logps/rejected": -254.49667358398438,
+      "loss": 0.4768,
+      "rewards/accuracies": 0.7333332896232605,
+      "rewards/chosen": -14.077960014343262,
+      "rewards/margins": 25.92667007446289,
+      "rewards/rejected": -40.00463104248047,
+      "step": 640
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 6.717397549018566,
+      "learning_rate": 2.848385192615339e-07,
+      "logits/chosen": 5637.56005859375,
+      "logits/rejected": 4628.1474609375,
+      "logps/chosen": -208.9348907470703,
+      "logps/rejected": -219.1776885986328,
+      "loss": 0.4814,
+      "rewards/accuracies": 0.8166667222976685,
+      "rewards/chosen": -12.61233139038086,
+      "rewards/margins": 37.836753845214844,
+      "rewards/rejected": -50.44908905029297,
+      "step": 650
+    },
+    {
+      "epoch": 0.5180533751962323,
+      "grad_norm": 6.838400431176198,
+      "learning_rate": 2.780397634492949e-07,
+      "logits/chosen": 6302.87744140625,
+      "logits/rejected": 5081.7353515625,
+      "logps/chosen": -229.68081665039062,
+      "logps/rejected": -247.7713165283203,
+      "loss": 0.4833,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -12.300036430358887,
+      "rewards/margins": 47.47599411010742,
+      "rewards/rejected": -59.776031494140625,
+      "step": 660
+    },
+    {
+      "epoch": 0.5259026687598116,
+      "grad_norm": 5.8476161724541535,
+      "learning_rate": 2.71219937000424e-07,
+      "logits/chosen": 6290.115234375,
+      "logits/rejected": 5202.7998046875,
+      "logps/chosen": -217.5615997314453,
+      "logps/rejected": -227.6338348388672,
+      "loss": 0.4827,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -10.82927131652832,
+      "rewards/margins": 27.942428588867188,
+      "rewards/rejected": -38.771697998046875,
+      "step": 670
+    },
+    {
+      "epoch": 0.533751962323391,
+      "grad_norm": 5.146890250240064,
+      "learning_rate": 2.6438416471154273e-07,
+      "logits/chosen": 6111.2451171875,
+      "logits/rejected": 5137.7705078125,
+      "logps/chosen": -222.5435028076172,
+      "logps/rejected": -225.12094116210938,
+      "loss": 0.4815,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -8.91177749633789,
+      "rewards/margins": 36.991119384765625,
+      "rewards/rejected": -45.902896881103516,
+      "step": 680
+    },
+    {
+      "epoch": 0.5416012558869702,
+      "grad_norm": 8.8935250283176,
+      "learning_rate": 2.5753758336186326e-07,
+      "logits/chosen": 6043.0673828125,
+      "logits/rejected": 5563.6806640625,
+      "logps/chosen": -221.37338256835938,
+      "logps/rejected": -271.20306396484375,
+      "loss": 0.48,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -12.23568344116211,
+      "rewards/margins": 42.76652145385742,
+      "rewards/rejected": -55.00220489501953,
+      "step": 690
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 5.847729785681332,
+      "learning_rate": 2.5068533785312666e-07,
+      "logits/chosen": 5745.1103515625,
+      "logits/rejected": 5549.70849609375,
+      "logps/chosen": -204.39468383789062,
+      "logps/rejected": -238.9816436767578,
+      "loss": 0.4882,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -15.167062759399414,
+      "rewards/margins": 36.86690139770508,
+      "rewards/rejected": -52.033958435058594,
+      "step": 700
+    },
+    {
+      "epoch": 0.5572998430141287,
+      "grad_norm": 4.903588308451907,
+      "learning_rate": 2.4383257734343794e-07,
+      "logits/chosen": 5706.705078125,
+      "logits/rejected": 5757.8916015625,
+      "logps/chosen": -205.46023559570312,
+      "logps/rejected": -243.0206756591797,
+      "loss": 0.4795,
+      "rewards/accuracies": 0.7750000953674316,
+      "rewards/chosen": -11.52241039276123,
+      "rewards/margins": 28.85659408569336,
+      "rewards/rejected": -40.37900924682617,
+      "step": 710
+    },
+    {
+      "epoch": 0.565149136577708,
+      "grad_norm": 4.5680367168979155,
+      "learning_rate": 2.3698445137790258e-07,
+      "logits/chosen": 6126.8349609375,
+      "logits/rejected": 5314.02001953125,
+      "logps/chosen": -227.4978790283203,
+      "logps/rejected": -240.22860717773438,
+      "loss": 0.4842,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -8.492025375366211,
+      "rewards/margins": 31.947551727294922,
+      "rewards/rejected": -40.4395751953125,
+      "step": 720
+    },
+    {
+      "epoch": 0.5729984301412873,
+      "grad_norm": 6.161642634958935,
+      "learning_rate": 2.3014610601897157e-07,
+      "logits/chosen": 6653.5546875,
+      "logits/rejected": 5136.146484375,
+      "logps/chosen": -238.821533203125,
+      "logps/rejected": -226.68203735351562,
+      "loss": 0.4792,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -13.643511772155762,
+      "rewards/margins": 37.98426818847656,
+      "rewards/rejected": -51.627777099609375,
+      "step": 730
+    },
+    {
+      "epoch": 0.5808477237048666,
+      "grad_norm": 5.261202948913745,
+      "learning_rate": 2.2332267997940513e-07,
+      "logits/chosen": 5534.0478515625,
+      "logits/rejected": 4724.48095703125,
+      "logps/chosen": -201.07333374023438,
+      "logps/rejected": -208.75173950195312,
+      "loss": 0.479,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -8.631407737731934,
+      "rewards/margins": 37.47869110107422,
+      "rewards/rejected": -46.1100959777832,
+      "step": 740
+    },
+    {
+      "epoch": 0.5886970172684458,
+      "grad_norm": 6.0896040319265285,
+      "learning_rate": 2.1651930076075723e-07,
+      "logits/chosen": 6029.47021484375,
+      "logits/rejected": 5496.3857421875,
+      "logps/chosen": -191.79519653320312,
+      "logps/rejected": -203.33026123046875,
+      "loss": 0.4819,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -11.413000106811523,
+      "rewards/margins": 24.80480194091797,
+      "rewards/rejected": -36.217803955078125,
+      "step": 750
+    },
+    {
+      "epoch": 0.5965463108320251,
+      "grad_norm": 4.761046588187656,
+      "learning_rate": 2.0974108080028692e-07,
+      "logits/chosen": 6314.89404296875,
+      "logits/rejected": 5032.1162109375,
+      "logps/chosen": -213.14517211914062,
+      "logps/rejected": -213.0286865234375,
+      "loss": 0.4832,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -9.876005172729492,
+      "rewards/margins": 28.655399322509766,
+      "rewards/rejected": -38.531402587890625,
+      "step": 760
+    },
+    {
+      "epoch": 0.6043956043956044,
+      "grad_norm": 7.508020905443514,
+      "learning_rate": 2.0299311362918773e-07,
+      "logits/chosen": 6520.9560546875,
+      "logits/rejected": 5636.296875,
+      "logps/chosen": -242.4247589111328,
+      "logps/rejected": -275.4010314941406,
+      "loss": 0.4821,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -12.711216926574707,
+      "rewards/margins": 38.81017303466797,
+      "rewards/rejected": -51.521385192871094,
+      "step": 770
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 5.044298723491718,
+      "learning_rate": 1.962804700450265e-07,
+      "logits/chosen": 6358.08837890625,
+      "logits/rejected": 6072.24560546875,
+      "logps/chosen": -226.471435546875,
+      "logps/rejected": -281.1588134765625,
+      "loss": 0.4829,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -10.3597993850708,
+      "rewards/margins": 33.39599609375,
+      "rewards/rejected": -43.75579071044922,
+      "step": 780
+    },
+    {
+      "epoch": 0.6200941915227629,
+      "grad_norm": 7.21284462490354,
+      "learning_rate": 1.8960819430126334e-07,
+      "logits/chosen": 5915.1435546875,
+      "logits/rejected": 5259.5546875,
+      "logps/chosen": -213.5358428955078,
+      "logps/rejected": -248.9722442626953,
+      "loss": 0.4792,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -15.374967575073242,
+      "rewards/margins": 44.96841049194336,
+      "rewards/rejected": -60.34337615966797,
+      "step": 790
+    },
+    {
+      "epoch": 0.6279434850863422,
+      "grad_norm": 6.911749315995225,
+      "learning_rate": 1.8298130031671972e-07,
+      "logits/chosen": 5912.0732421875,
+      "logits/rejected": 5204.81982421875,
+      "logps/chosen": -231.18405151367188,
+      "logps/rejected": -258.3150634765625,
+      "loss": 0.4837,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -14.43272876739502,
+      "rewards/margins": 31.22930335998535,
+      "rewards/rejected": -45.66203689575195,
+      "step": 800
+    },
+    {
+      "epoch": 0.6357927786499215,
+      "grad_norm": 5.218511863000425,
+      "learning_rate": 1.7640476790784075e-07,
+      "logits/chosen": 5465.1982421875,
+      "logits/rejected": 4933.3720703125,
+      "logps/chosen": -213.6913299560547,
+      "logps/rejected": -266.97265625,
+      "loss": 0.4817,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -11.240377426147461,
+      "rewards/margins": 34.471500396728516,
+      "rewards/rejected": -45.71187973022461,
+      "step": 810
+    },
+    {
+      "epoch": 0.6436420722135008,
+      "grad_norm": 7.438249570403255,
+      "learning_rate": 1.6988353904658492e-07,
+      "logits/chosen": 5941.025390625,
+      "logits/rejected": 4626.3564453125,
+      "logps/chosen": -229.0679931640625,
+      "logps/rejected": -208.60195922851562,
+      "loss": 0.478,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -7.8618903160095215,
+      "rewards/margins": 32.07147216796875,
+      "rewards/rejected": -39.9333610534668,
+      "step": 820
+    },
+    {
+      "epoch": 0.6514913657770801,
+      "grad_norm": 8.778626873186747,
+      "learning_rate": 1.634225141467513e-07,
+      "logits/chosen": 5877.83447265625,
+      "logits/rejected": 5282.060546875,
+      "logps/chosen": -219.01065063476562,
+      "logps/rejected": -245.612548828125,
+      "loss": 0.4805,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -14.819755554199219,
+      "rewards/margins": 38.319461822509766,
+      "rewards/rejected": -53.13921356201172,
+      "step": 830
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 4.992529477045905,
+      "learning_rate": 1.570265483815364e-07,
+      "logits/chosen": 6424.9462890625,
+      "logits/rejected": 5295.16552734375,
+      "logps/chosen": -244.10525512695312,
+      "logps/rejected": -261.36346435546875,
+      "loss": 0.481,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -16.73971176147461,
+      "rewards/margins": 31.8198299407959,
+      "rewards/rejected": -48.559547424316406,
+      "step": 840
+    },
+    {
+      "epoch": 0.6671899529042387,
+      "grad_norm": 7.542089334458241,
+      "learning_rate": 1.5070044803508691e-07,
+      "logits/chosen": 5939.9482421875,
+      "logits/rejected": 5369.12841796875,
+      "logps/chosen": -227.2097930908203,
+      "logps/rejected": -252.93820190429688,
+      "loss": 0.4772,
+      "rewards/accuracies": 0.7166667580604553,
+      "rewards/chosen": -11.733682632446289,
+      "rewards/margins": 40.6881217956543,
+      "rewards/rejected": -52.42180252075195,
+      "step": 850
+    },
+    {
+      "epoch": 0.6750392464678179,
+      "grad_norm": 10.41273121619664,
+      "learning_rate": 1.444489668907914e-07,
+      "logits/chosen": 6402.37109375,
+      "logits/rejected": 5468.13134765625,
+      "logps/chosen": -258.1214599609375,
+      "logps/rejected": -253.7722625732422,
+      "loss": 0.4809,
+      "rewards/accuracies": 0.8000000715255737,
+      "rewards/chosen": -10.320735931396484,
+      "rewards/margins": 40.777584075927734,
+      "rewards/rejected": -51.098323822021484,
+      "step": 860
+    },
+    {
+      "epoch": 0.6828885400313972,
+      "grad_norm": 5.248825341405066,
+      "learning_rate": 1.3827680265902232e-07,
+      "logits/chosen": 6361.248046875,
+      "logits/rejected": 5298.61572265625,
+      "logps/chosen": -243.3575439453125,
+      "logps/rejected": -250.5015106201172,
+      "loss": 0.4825,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -13.222381591796875,
+      "rewards/margins": 36.560760498046875,
+      "rewards/rejected": -49.783138275146484,
+      "step": 870
+    },
+    {
+      "epoch": 0.6907378335949764,
+      "grad_norm": 8.056127375196619,
+      "learning_rate": 1.3218859344701632e-07,
+      "logits/chosen": 5598.6044921875,
+      "logits/rejected": 5378.14208984375,
+      "logps/chosen": -221.2474822998047,
+      "logps/rejected": -275.5020446777344,
+      "loss": 0.4827,
+      "rewards/accuracies": 0.7249999642372131,
+      "rewards/chosen": -10.712526321411133,
+      "rewards/margins": 33.19308853149414,
+      "rewards/rejected": -43.90561294555664,
+      "step": 880
+    },
+    {
+      "epoch": 0.6985871271585558,
+      "grad_norm": 6.462283230726811,
+      "learning_rate": 1.2618891427354172e-07,
+      "logits/chosen": 6601.6826171875,
+      "logits/rejected": 5406.0244140625,
+      "logps/chosen": -266.26226806640625,
+      "logps/rejected": -258.1165466308594,
+      "loss": 0.4824,
+      "rewards/accuracies": 0.8083332777023315,
+      "rewards/chosen": -8.635444641113281,
+      "rewards/margins": 37.71168518066406,
+      "rewards/rejected": -46.347129821777344,
+      "step": 890
+    },
+    {
+      "epoch": 0.706436420722135,
+      "grad_norm": 7.146931701552703,
+      "learning_rate": 1.202822736309758e-07,
+      "logits/chosen": 5596.5810546875,
+      "logits/rejected": 5215.19140625,
+      "logps/chosen": -214.41629028320312,
+      "logps/rejected": -253.17379760742188,
+      "loss": 0.4815,
+      "rewards/accuracies": 0.73333340883255,
+      "rewards/chosen": -10.091071128845215,
+      "rewards/margins": 32.64034652709961,
+      "rewards/rejected": -42.731414794921875,
+      "step": 900
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 6.45263078416188,
+      "learning_rate": 1.1447311009737299e-07,
+      "logits/chosen": 5508.6884765625,
+      "logits/rejected": 5250.3154296875,
+      "logps/chosen": -222.135986328125,
+      "logps/rejected": -262.9181213378906,
+      "loss": 0.4803,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -13.866915702819824,
+      "rewards/margins": 41.107566833496094,
+      "rewards/rejected": -54.97447967529297,
+      "step": 910
+    },
+    {
+      "epoch": 0.7221350078492935,
+      "grad_norm": 5.759526286673952,
+      "learning_rate": 1.0876578900107053e-07,
+      "logits/chosen": 6085.29931640625,
+      "logits/rejected": 5071.2158203125,
+      "logps/chosen": -246.2467498779297,
+      "logps/rejected": -252.5704803466797,
+      "loss": 0.4796,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -13.800603866577148,
+      "rewards/margins": 40.584354400634766,
+      "rewards/rejected": -54.38496017456055,
+      "step": 920
+    },
+    {
+      "epoch": 0.7299843014128728,
+      "grad_norm": 5.35980955418667,
+      "learning_rate": 1.0316459914033793e-07,
+      "logits/chosen": 5992.89306640625,
+      "logits/rejected": 4551.4521484375,
+      "logps/chosen": -253.8580780029297,
+      "logps/rejected": -241.84286499023438,
+      "loss": 0.4835,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -17.851383209228516,
+      "rewards/margins": 38.075477600097656,
+      "rewards/rejected": -55.9268684387207,
+      "step": 930
+    },
+    {
+      "epoch": 0.7378335949764521,
+      "grad_norm": 5.546184868537026,
+      "learning_rate": 9.767374956053584e-08,
+      "logits/chosen": 5804.6865234375,
+      "logits/rejected": 5108.57958984375,
+      "logps/chosen": -231.1918182373047,
+      "logps/rejected": -260.5343017578125,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -12.856742858886719,
+      "rewards/margins": 42.71269989013672,
+      "rewards/rejected": -55.569435119628906,
+      "step": 940
+    },
+    {
+      "epoch": 0.7456828885400314,
+      "grad_norm": 5.310959910799943,
+      "learning_rate": 9.229736639120561e-08,
+      "logits/chosen": 5984.3681640625,
+      "logits/rejected": 5550.1865234375,
+      "logps/chosen": -229.02523803710938,
+      "logps/rejected": -247.6044464111328,
+      "loss": 0.4835,
+      "rewards/accuracies": 0.7833333611488342,
+      "rewards/chosen": -11.238405227661133,
+      "rewards/margins": 22.278400421142578,
+      "rewards/rejected": -33.516807556152344,
+      "step": 950
+    },
+    {
+      "epoch": 0.7535321821036107,
+      "grad_norm": 5.724504063036896,
+      "learning_rate": 8.70394897454659e-08,
+      "logits/chosen": 5837.259765625,
+      "logits/rejected": 5220.193359375,
+      "logps/chosen": -226.56478881835938,
+      "logps/rejected": -249.77938842773438,
+      "loss": 0.4772,
+      "rewards/accuracies": 0.8083332777023315,
+      "rewards/chosen": -8.066027641296387,
+      "rewards/margins": 39.250091552734375,
+      "rewards/rejected": -47.31611633300781,
+      "step": 960
+    },
+    {
+      "epoch": 0.7613814756671899,
+      "grad_norm": 6.84872456451459,
+      "learning_rate": 8.19040706840472e-08,
+      "logits/chosen": 5938.76025390625,
+      "logits/rejected": 5001.06396484375,
+      "logps/chosen": -251.7744598388672,
+      "logps/rejected": -265.7369689941406,
+      "loss": 0.4772,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -11.534469604492188,
+      "rewards/margins": 47.53069305419922,
+      "rewards/rejected": -59.065155029296875,
+      "step": 970
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 6.2584137075852455,
+      "learning_rate": 7.689496824624525e-08,
+      "logits/chosen": 5646.22802734375,
+      "logits/rejected": 4573.884765625,
+      "logps/chosen": -238.1552276611328,
+      "logps/rejected": -266.3992614746094,
+      "loss": 0.4767,
+      "rewards/accuracies": 0.8333333134651184,
+      "rewards/chosen": -9.31987190246582,
+      "rewards/margins": 66.60228729248047,
+      "rewards/rejected": -75.92216491699219,
+      "step": 980
+    },
+    {
+      "epoch": 0.7770800627943485,
+      "grad_norm": 8.467713398392366,
+      "learning_rate": 7.201594655002458e-08,
+      "logits/chosen": 5968.3173828125,
+      "logits/rejected": 5018.83740234375,
+      "logps/chosen": -242.1980438232422,
+      "logps/rejected": -261.9761657714844,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -16.304744720458984,
+      "rewards/margins": 51.60383987426758,
+      "rewards/rejected": -67.90858459472656,
+      "step": 990
+    },
+    {
+      "epoch": 0.7849293563579278,
+      "grad_norm": 7.778614626465624,
+      "learning_rate": 6.727067196345099e-08,
+      "logits/chosen": 5659.57275390625,
+      "logits/rejected": 4817.7607421875,
+      "logps/chosen": -226.59005737304688,
+      "logps/rejected": -226.68734741210938,
+      "loss": 0.4817,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -12.7899169921875,
+      "rewards/margins": 33.538944244384766,
+      "rewards/rejected": -46.328861236572266,
+      "step": 1000
+    },
+    {
+      "epoch": 0.792778649921507,
+      "grad_norm": 6.403550827254964,
+      "learning_rate": 6.26627103495786e-08,
+      "logits/chosen": 5840.86767578125,
+      "logits/rejected": 4903.9775390625,
+      "logps/chosen": -223.2283477783203,
+      "logps/rejected": -242.93466186523438,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -8.5188570022583,
+      "rewards/margins": 43.02119064331055,
+      "rewards/rejected": -51.54004669189453,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8006279434850864,
+      "grad_norm": 5.514137797353558,
+      "learning_rate": 5.8195524386862374e-08,
+      "logits/chosen": 5926.3291015625,
+      "logits/rejected": 5305.26318359375,
+      "logps/chosen": -256.4900207519531,
+      "logps/rejected": -274.34906005859375,
+      "loss": 0.4821,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -8.3116455078125,
+      "rewards/margins": 39.88562774658203,
+      "rewards/rejected": -48.19727325439453,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8084772370486656,
+      "grad_norm": 5.221372206353793,
+      "learning_rate": 5.38724709671092e-08,
+      "logits/chosen": 6330.0234375,
+      "logits/rejected": 6003.18408203125,
+      "logps/chosen": -241.54736328125,
+      "logps/rejected": -281.74896240234375,
+      "loss": 0.4787,
+      "rewards/accuracies": 0.783333420753479,
+      "rewards/chosen": -10.10380744934082,
+      "rewards/margins": 38.526222229003906,
+      "rewards/rejected": -48.630027770996094,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 7.932681835732521,
+      "learning_rate": 4.969679867292276e-08,
+      "logits/chosen": 5629.4482421875,
+      "logits/rejected": 5160.17578125,
+      "logps/chosen": -234.3016357421875,
+      "logps/rejected": -264.07110595703125,
+      "loss": 0.4798,
+      "rewards/accuracies": 0.7166667580604553,
+      "rewards/chosen": -14.211596488952637,
+      "rewards/margins": 40.67064666748047,
+      "rewards/rejected": -54.88224411010742,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 6.9567227767775615,
+      "learning_rate": 4.5671645336537416e-08,
+      "logits/chosen": 5678.796875,
+      "logits/rejected": 5205.8046875,
+      "logps/chosen": -250.764404296875,
+      "logps/rejected": -270.3853759765625,
+      "loss": 0.4788,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -13.21537971496582,
+      "rewards/margins": 41.3323860168457,
+      "rewards/rejected": -54.54777145385742,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8320251177394035,
+      "grad_norm": 11.260543191909672,
+      "learning_rate": 4.180003568187776e-08,
+      "logits/chosen": 7013.36181640625,
+      "logits/rejected": 5547.8046875,
+      "logps/chosen": -277.34161376953125,
+      "logps/rejected": -266.3480224609375,
+      "loss": 0.4853,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -16.316293716430664,
+      "rewards/margins": 29.96787452697754,
+      "rewards/rejected": -46.28417205810547,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8398744113029827,
+      "grad_norm": 5.873157048382797,
+      "learning_rate": 3.8084879051612144e-08,
+      "logits/chosen": 5843.4775390625,
+      "logits/rejected": 5391.5986328125,
+      "logps/chosen": -234.66769409179688,
+      "logps/rejected": -239.1238555908203,
+      "loss": 0.4805,
+      "rewards/accuracies": 0.73333340883255,
+      "rewards/chosen": -9.391263961791992,
+      "rewards/margins": 36.595001220703125,
+      "rewards/rejected": -45.98626708984375,
+      "step": 1070
+    },
+    {
+      "epoch": 0.847723704866562,
+      "grad_norm": 6.007255893505933,
+      "learning_rate": 3.452896722091128e-08,
+      "logits/chosen": 6401.373046875,
+      "logits/rejected": 4987.56005859375,
+      "logps/chosen": -275.00115966796875,
+      "logps/rejected": -255.5666046142578,
+      "loss": 0.4771,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -8.407303810119629,
+      "rewards/margins": 46.17400360107422,
+      "rewards/rejected": -54.5813102722168,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8555729984301413,
+      "grad_norm": 6.959675987878217,
+      "learning_rate": 3.11349722995527e-08,
+      "logits/chosen": 6485.73193359375,
+      "logits/rejected": 4893.6123046875,
+      "logps/chosen": -240.83041381835938,
+      "logps/rejected": -262.59429931640625,
+      "loss": 0.4823,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -13.316200256347656,
+      "rewards/margins": 36.36842727661133,
+      "rewards/rejected": -49.684635162353516,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8634222919937206,
+      "grad_norm": 6.728053574170472,
+      "learning_rate": 2.7905444723949762e-08,
+      "logits/chosen": 6255.11572265625,
+      "logits/rejected": 5196.1142578125,
+      "logps/chosen": -252.09976196289062,
+      "logps/rejected": -247.3374786376953,
+      "loss": 0.4814,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -13.543619155883789,
+      "rewards/margins": 44.29808807373047,
+      "rewards/rejected": -57.841705322265625,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8712715855572999,
+      "grad_norm": 6.249434590126908,
+      "learning_rate": 2.484281134061142e-08,
+      "logits/chosen": 6619.61474609375,
+      "logits/rejected": 5369.69189453125,
+      "logps/chosen": -277.9066162109375,
+      "logps/rejected": -277.1863708496094,
+      "loss": 0.4815,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -13.30717658996582,
+      "rewards/margins": 41.61245346069336,
+      "rewards/rejected": -54.91962814331055,
+      "step": 1110
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 6.621447418753569,
+      "learning_rate": 2.194937358247506e-08,
+      "logits/chosen": 6474.90234375,
+      "logits/rejected": 5295.9033203125,
+      "logps/chosen": -260.36065673828125,
+      "logps/rejected": -271.5030517578125,
+      "loss": 0.479,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -15.229601860046387,
+      "rewards/margins": 39.49894332885742,
+      "rewards/rejected": -54.728553771972656,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8869701726844584,
+      "grad_norm": 8.33446410604382,
+      "learning_rate": 1.9227305739481612e-08,
+      "logits/chosen": 5892.1806640625,
+      "logits/rejected": 4676.626953125,
+      "logps/chosen": -243.70510864257812,
+      "logps/rejected": -232.04556274414062,
+      "loss": 0.4778,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -8.918004989624023,
+      "rewards/margins": 42.899051666259766,
+      "rewards/rejected": -51.81705856323242,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8948194662480377,
+      "grad_norm": 5.6890326351976155,
+      "learning_rate": 1.6678653324693787e-08,
+      "logits/chosen": 6475.4951171875,
+      "logits/rejected": 5299.70751953125,
+      "logps/chosen": -269.6833190917969,
+      "logps/rejected": -268.32513427734375,
+      "loss": 0.4802,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -12.040689468383789,
+      "rewards/margins": 35.418983459472656,
+      "rewards/rejected": -47.459678649902344,
+      "step": 1140
+    },
+    {
+      "epoch": 0.902668759811617,
+      "grad_norm": 6.048036034423531,
+      "learning_rate": 1.4305331537183384e-08,
+      "logits/chosen": 5732.1220703125,
+      "logits/rejected": 5299.99560546875,
+      "logps/chosen": -238.8845977783203,
+      "logps/rejected": -264.5845031738281,
+      "loss": 0.478,
+      "rewards/accuracies": 0.7166667580604553,
+      "rewards/chosen": -11.897860527038574,
+      "rewards/margins": 33.151702880859375,
+      "rewards/rejected": -45.04956817626953,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9105180533751962,
+      "grad_norm": 5.848377321734073,
+      "learning_rate": 1.2109123822844653e-08,
+      "logits/chosen": 5896.5595703125,
+      "logits/rejected": 4711.38427734375,
+      "logps/chosen": -243.69515991210938,
+      "logps/rejected": -245.3145751953125,
+      "loss": 0.4802,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -15.122274398803711,
+      "rewards/margins": 34.2625846862793,
+      "rewards/rejected": -49.384857177734375,
+      "step": 1160
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 5.838867657991871,
+      "learning_rate": 1.0091680534213387e-08,
+      "logits/chosen": 6464.91552734375,
+      "logits/rejected": 6239.65771484375,
+      "logps/chosen": -256.83367919921875,
+      "logps/rejected": -294.30145263671875,
+      "loss": 0.4816,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -13.878461837768555,
+      "rewards/margins": 33.63318634033203,
+      "rewards/rejected": -47.511653900146484,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9262166405023547,
+      "grad_norm": 6.801398869039188,
+      "learning_rate": 8.254517690300944e-09,
+      "logits/chosen": 5692.70703125,
+      "logits/rejected": 5195.38525390625,
+      "logps/chosen": -251.6653289794922,
+      "logps/rejected": -267.250244140625,
+      "loss": 0.4814,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -11.756540298461914,
+      "rewards/margins": 38.70287322998047,
+      "rewards/rejected": -50.45941925048828,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9340659340659341,
+      "grad_norm": 5.963443433951819,
+      "learning_rate": 6.599015837372907e-09,
+      "logits/chosen": 6176.25244140625,
+      "logits/rejected": 5420.193359375,
+      "logps/chosen": -269.15130615234375,
+      "logps/rejected": -276.1173095703125,
+      "loss": 0.479,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -20.287494659423828,
+      "rewards/margins": 38.67988586425781,
+      "rewards/rejected": -58.967376708984375,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9419152276295133,
+      "grad_norm": 6.813232634060442,
+      "learning_rate": 5.126419011529992e-09,
+      "logits/chosen": 6387.81396484375,
+      "logits/rejected": 5468.4169921875,
+      "logps/chosen": -266.6917724609375,
+      "logps/rejected": -276.78839111328125,
+      "loss": 0.4785,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -11.047189712524414,
+      "rewards/margins": 47.05707931518555,
+      "rewards/rejected": -58.104270935058594,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9497645211930926,
+      "grad_norm": 9.80121981882165,
+      "learning_rate": 3.837833803870177e-09,
+      "logits/chosen": 5973.63623046875,
+      "logits/rejected": 5258.65087890625,
+      "logps/chosen": -252.6921844482422,
+      "logps/rejected": -273.18035888671875,
+      "loss": 0.4811,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -12.484926223754883,
+      "rewards/margins": 42.53102493286133,
+      "rewards/rejected": -55.01594924926758,
+      "step": 1210
+    },
+    {
+      "epoch": 0.957613814756672,
+      "grad_norm": 7.203558153981481,
+      "learning_rate": 2.734228528934679e-09,
+      "logits/chosen": 7448.9443359375,
+      "logits/rejected": 5512.33203125,
+      "logps/chosen": -312.1805725097656,
+      "logps/rejected": -300.3201904296875,
+      "loss": 0.4817,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -15.350790023803711,
+      "rewards/margins": 39.79079055786133,
+      "rewards/rejected": -55.14158248901367,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9654631083202512,
+      "grad_norm": 6.776742127412717,
+      "learning_rate": 1.8164324970625645e-09,
+      "logits/chosen": 6630.1591796875,
+      "logits/rejected": 5257.56298828125,
+      "logps/chosen": -270.0474548339844,
+      "logps/rejected": -263.6984558105469,
+      "loss": 0.4803,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -9.480215072631836,
+      "rewards/margins": 41.2264289855957,
+      "rewards/rejected": -50.706642150878906,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9733124018838305,
+      "grad_norm": 5.426445939101484,
+      "learning_rate": 1.0851353912008642e-09,
+      "logits/chosen": 5712.93408203125,
+      "logits/rejected": 5265.7021484375,
+      "logps/chosen": -247.56008911132812,
+      "logps/rejected": -291.08746337890625,
+      "loss": 0.4786,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -15.966026306152344,
+      "rewards/margins": 39.92435073852539,
+      "rewards/rejected": -55.890380859375,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9811616954474097,
+      "grad_norm": 5.411171726240316,
+      "learning_rate": 5.408867486384471e-10,
+      "logits/chosen": 5824.78125,
+      "logits/rejected": 4941.5732421875,
+      "logps/chosen": -240.45315551757812,
+      "logps/rejected": -232.99081420898438,
+      "loss": 0.4813,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -10.121699333190918,
+      "rewards/margins": 33.4198112487793,
+      "rewards/rejected": -43.54151153564453,
+      "step": 1250
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 6.255102070301854,
+      "learning_rate": 1.840955480532924e-10,
+      "logits/chosen": 5502.2841796875,
+      "logits/rejected": 5238.97265625,
+      "logps/chosen": -245.449951171875,
+      "logps/rejected": -261.3154296875,
+      "loss": 0.4794,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -13.299115180969238,
+      "rewards/margins": 31.690093994140625,
+      "rewards/rejected": -44.98920822143555,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9968602825745683,
+      "grad_norm": 6.339307198379936,
+      "learning_rate": 1.502990218302247e-11,
+      "logits/chosen": 5779.14501953125,
+      "logits/rejected": 4718.3759765625,
+      "logps/chosen": -237.53652954101562,
+      "logps/rejected": -237.6223907470703,
+      "loss": 0.4789,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -13.04780101776123,
+      "rewards/margins": 38.266212463378906,
+      "rewards/rejected": -51.31401443481445,
+      "step": 1270
+    },
+    {
+      "epoch": 1.0,
+      "step": 1274,
+      "total_flos": 0.0,
+      "train_loss": 0.4838377035206865,
+      "train_runtime": 15889.6187,
+      "train_samples_per_second": 3.847,
+      "train_steps_per_second": 0.08
+    }
+  ],
+  "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
+}