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_ExponentialAll-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_ExponentialAll-7b-sft-full
+
+This model is a fine-tuned version of [TTTXXX01/All_like-zephyr-7b-sft-full](https://huggingface.co/TTTXXX01/All_like-zephyr-7b-sft-full) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 6
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 48
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 1.9640779633724146,
+    "train_runtime": 14760.7646,
+    "train_samples": 61135,
+    "train_samples_per_second": 4.142,
+    "train_steps_per_second": 0.086
+}

generation_config.json

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

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7615ab5a171b70c63c62ca7cfe03895f7ba445cdd59b41f3bf041915ded243fc
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde887d137aa9090c8f858c7cca0c50ce9f22b2665d60a8c3b965f910e53bf99
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f65009a074312800b22403cda0873fb77e6324dc332c553fcc3be51cf3c44e
+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": 1.9640779633724146,
+    "train_runtime": 14760.7646,
+    "train_samples": 61135,
+    "train_samples_per_second": 4.142,
+    "train_steps_per_second": 0.086
+}

trainer_state.json

@@ -0,0 +1,1962 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1274,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0007849293563579278,
+      "grad_norm": 6.091750131963952,
+      "learning_rate": 3.90625e-09,
+      "logits/chosen": 5914.52099609375,
+      "logits/rejected": 2785.021484375,
+      "logps/chosen": -212.45889282226562,
+      "logps/rejected": -98.59669494628906,
+      "loss": 2.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.007849293563579277,
+      "grad_norm": 6.059369066138964,
+      "learning_rate": 3.9062499999999997e-08,
+      "logits/chosen": 4973.767578125,
+      "logits/rejected": 4328.24365234375,
+      "logps/chosen": -204.23040771484375,
+      "logps/rejected": -179.6959686279297,
+      "loss": 2.0,
+      "rewards/accuracies": 0.4351852238178253,
+      "rewards/chosen": 0.05348973721265793,
+      "rewards/margins": 0.04383070021867752,
+      "rewards/rejected": 0.009659038856625557,
+      "step": 10
+    },
+    {
+      "epoch": 0.015698587127158554,
+      "grad_norm": 6.2041398306498685,
+      "learning_rate": 7.812499999999999e-08,
+      "logits/chosen": 6084.0126953125,
+      "logits/rejected": 4834.15869140625,
+      "logps/chosen": -217.233642578125,
+      "logps/rejected": -196.76730346679688,
+      "loss": 2.0,
+      "rewards/accuracies": 0.4833333492279053,
+      "rewards/chosen": -0.02243190072476864,
+      "rewards/margins": 0.03131182864308357,
+      "rewards/rejected": -0.053743720054626465,
+      "step": 20
+    },
+    {
+      "epoch": 0.023547880690737835,
+      "grad_norm": 5.475152737188952,
+      "learning_rate": 1.1718749999999999e-07,
+      "logits/chosen": 6084.05908203125,
+      "logits/rejected": 5104.91748046875,
+      "logps/chosen": -250.56375122070312,
+      "logps/rejected": -209.34457397460938,
+      "loss": 1.9999,
+      "rewards/accuracies": 0.5333333015441895,
+      "rewards/chosen": 0.008603035472333431,
+      "rewards/margins": 0.05558818578720093,
+      "rewards/rejected": -0.04698514938354492,
+      "step": 30
+    },
+    {
+      "epoch": 0.03139717425431711,
+      "grad_norm": 5.690781670053855,
+      "learning_rate": 1.5624999999999999e-07,
+      "logits/chosen": 5311.8642578125,
+      "logits/rejected": 4346.90673828125,
+      "logps/chosen": -211.9870147705078,
+      "logps/rejected": -181.72384643554688,
+      "loss": 1.9997,
+      "rewards/accuracies": 0.5333333015441895,
+      "rewards/chosen": 0.09225504100322723,
+      "rewards/margins": 0.12906396389007568,
+      "rewards/rejected": -0.036808937788009644,
+      "step": 40
+    },
+    {
+      "epoch": 0.03924646781789639,
+      "grad_norm": 5.758835415832506,
+      "learning_rate": 1.9531249999999998e-07,
+      "logits/chosen": 6425.0869140625,
+      "logits/rejected": 5042.13916015625,
+      "logps/chosen": -265.3288879394531,
+      "logps/rejected": -206.8175048828125,
+      "loss": 1.9992,
+      "rewards/accuracies": 0.6666667461395264,
+      "rewards/chosen": 0.29770660400390625,
+      "rewards/margins": 0.4155918061733246,
+      "rewards/rejected": -0.11788525432348251,
+      "step": 50
+    },
+    {
+      "epoch": 0.04709576138147567,
+      "grad_norm": 5.552781734195383,
+      "learning_rate": 2.3437499999999998e-07,
+      "logits/chosen": 5484.19091796875,
+      "logits/rejected": 4559.71923828125,
+      "logps/chosen": -213.75491333007812,
+      "logps/rejected": -209.1690216064453,
+      "loss": 1.9986,
+      "rewards/accuracies": 0.6666666269302368,
+      "rewards/chosen": 0.24906444549560547,
+      "rewards/margins": 0.6179634928703308,
+      "rewards/rejected": -0.36889898777008057,
+      "step": 60
+    },
+    {
+      "epoch": 0.054945054945054944,
+      "grad_norm": 5.377299650407647,
+      "learning_rate": 2.734375e-07,
+      "logits/chosen": 5194.39501953125,
+      "logits/rejected": 4918.55322265625,
+      "logps/chosen": -178.2979736328125,
+      "logps/rejected": -177.39535522460938,
+      "loss": 1.998,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": 0.18295133113861084,
+      "rewards/margins": 0.8465949892997742,
+      "rewards/rejected": -0.6636435985565186,
+      "step": 70
+    },
+    {
+      "epoch": 0.06279434850863422,
+      "grad_norm": 5.650017423938731,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": 5774.41748046875,
+      "logits/rejected": 5269.755859375,
+      "logps/chosen": -196.76974487304688,
+      "logps/rejected": -182.98446655273438,
+      "loss": 1.9959,
+      "rewards/accuracies": 0.6500000357627869,
+      "rewards/chosen": -0.20117223262786865,
+      "rewards/margins": 1.1927589178085327,
+      "rewards/rejected": -1.3939311504364014,
+      "step": 80
+    },
+    {
+      "epoch": 0.0706436420722135,
+      "grad_norm": 6.605265759829803,
+      "learning_rate": 3.5156249999999997e-07,
+      "logits/chosen": 6039.5634765625,
+      "logits/rejected": 5181.203125,
+      "logps/chosen": -220.1410675048828,
+      "logps/rejected": -190.4438934326172,
+      "loss": 1.9924,
+      "rewards/accuracies": 0.7583332657814026,
+      "rewards/chosen": -1.2588454484939575,
+      "rewards/margins": 4.741243362426758,
+      "rewards/rejected": -6.000088691711426,
+      "step": 90
+    },
+    {
+      "epoch": 0.07849293563579278,
+      "grad_norm": 7.213834973026546,
+      "learning_rate": 3.9062499999999997e-07,
+      "logits/chosen": 5967.2626953125,
+      "logits/rejected": 5745.4873046875,
+      "logps/chosen": -213.9269256591797,
+      "logps/rejected": -208.77261352539062,
+      "loss": 1.9932,
+      "rewards/accuracies": 0.6750000715255737,
+      "rewards/chosen": -3.696242094039917,
+      "rewards/margins": 5.634647369384766,
+      "rewards/rejected": -9.330889701843262,
+      "step": 100
+    },
+    {
+      "epoch": 0.08634222919937205,
+      "grad_norm": 6.156201133938342,
+      "learning_rate": 4.2968749999999996e-07,
+      "logits/chosen": 6470.56884765625,
+      "logits/rejected": 5289.95849609375,
+      "logps/chosen": -188.42457580566406,
+      "logps/rejected": -190.61293029785156,
+      "loss": 1.9887,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -5.309735298156738,
+      "rewards/margins": 6.310976982116699,
+      "rewards/rejected": -11.620712280273438,
+      "step": 110
+    },
+    {
+      "epoch": 0.09419152276295134,
+      "grad_norm": 8.999184508333663,
+      "learning_rate": 4.6874999999999996e-07,
+      "logits/chosen": 6397.328125,
+      "logits/rejected": 5324.27587890625,
+      "logps/chosen": -210.2899169921875,
+      "logps/rejected": -212.7317657470703,
+      "loss": 1.9865,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -7.453166961669922,
+      "rewards/margins": 7.11349630355835,
+      "rewards/rejected": -14.56666374206543,
+      "step": 120
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 6.546135911338803,
+      "learning_rate": 4.999962424962166e-07,
+      "logits/chosen": 6333.814453125,
+      "logits/rejected": 5863.9287109375,
+      "logps/chosen": -215.83139038085938,
+      "logps/rejected": -212.8985137939453,
+      "loss": 1.9843,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -6.0229082107543945,
+      "rewards/margins": 9.231057167053223,
+      "rewards/rejected": -15.2539644241333,
+      "step": 130
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 7.874723764445264,
+      "learning_rate": 4.998647417232375e-07,
+      "logits/chosen": 6198.4814453125,
+      "logits/rejected": 5459.091796875,
+      "logps/chosen": -195.5287628173828,
+      "logps/rejected": -197.17437744140625,
+      "loss": 1.983,
+      "rewards/accuracies": 0.6333333849906921,
+      "rewards/chosen": -9.861322402954102,
+      "rewards/margins": 9.721135139465332,
+      "rewards/rejected": -19.582454681396484,
+      "step": 140
+    },
+    {
+      "epoch": 0.11773940345368916,
+      "grad_norm": 9.20471530543848,
+      "learning_rate": 4.995454786965036e-07,
+      "logits/chosen": 6376.53857421875,
+      "logits/rejected": 5328.8974609375,
+      "logps/chosen": -210.15576171875,
+      "logps/rejected": -192.92373657226562,
+      "loss": 1.98,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -8.471376419067383,
+      "rewards/margins": 12.154645919799805,
+      "rewards/rejected": -20.626020431518555,
+      "step": 150
+    },
+    {
+      "epoch": 0.12558869701726844,
+      "grad_norm": 7.461193923622369,
+      "learning_rate": 4.990386933279972e-07,
+      "logits/chosen": 6318.7490234375,
+      "logits/rejected": 5644.8623046875,
+      "logps/chosen": -207.67337036132812,
+      "logps/rejected": -219.74203491210938,
+      "loss": 1.9794,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -10.14518928527832,
+      "rewards/margins": 12.539278984069824,
+      "rewards/rejected": -22.684467315673828,
+      "step": 160
+    },
+    {
+      "epoch": 0.13343799058084774,
+      "grad_norm": 6.508017494074614,
+      "learning_rate": 4.983447664444096e-07,
+      "logits/chosen": 6519.24169921875,
+      "logits/rejected": 5813.3642578125,
+      "logps/chosen": -220.01766967773438,
+      "logps/rejected": -216.58914184570312,
+      "loss": 1.9806,
+      "rewards/accuracies": 0.6583333611488342,
+      "rewards/chosen": -10.396989822387695,
+      "rewards/margins": 9.870583534240723,
+      "rewards/rejected": -20.267574310302734,
+      "step": 170
+    },
+    {
+      "epoch": 0.141287284144427,
+      "grad_norm": 7.695429851231189,
+      "learning_rate": 4.97464219500968e-07,
+      "logits/chosen": 5723.25439453125,
+      "logits/rejected": 5001.2041015625,
+      "logps/chosen": -198.26637268066406,
+      "logps/rejected": -199.6933135986328,
+      "loss": 1.977,
+      "rewards/accuracies": 0.6500000357627869,
+      "rewards/chosen": -9.738619804382324,
+      "rewards/margins": 11.793425559997559,
+      "rewards/rejected": -21.532047271728516,
+      "step": 180
+    },
+    {
+      "epoch": 0.14913657770800628,
+      "grad_norm": 8.229494993248766,
+      "learning_rate": 4.963977141895843e-07,
+      "logits/chosen": 5866.8330078125,
+      "logits/rejected": 5040.8291015625,
+      "logps/chosen": -214.79452514648438,
+      "logps/rejected": -226.88827514648438,
+      "loss": 1.9734,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -11.035551071166992,
+      "rewards/margins": 24.613243103027344,
+      "rewards/rejected": -35.6487922668457,
+      "step": 190
+    },
+    {
+      "epoch": 0.15698587127158556,
+      "grad_norm": 8.986914548041765,
+      "learning_rate": 4.951460519416227e-07,
+      "logits/chosen": 5760.6181640625,
+      "logits/rejected": 5327.140625,
+      "logps/chosen": -192.12252807617188,
+      "logps/rejected": -224.0847930908203,
+      "loss": 1.9722,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -9.578254699707031,
+      "rewards/margins": 17.835506439208984,
+      "rewards/rejected": -27.413761138916016,
+      "step": 200
+    },
+    {
+      "epoch": 0.16483516483516483,
+      "grad_norm": 11.60946438594492,
+      "learning_rate": 4.937101733256606e-07,
+      "logits/chosen": 5221.634765625,
+      "logits/rejected": 4657.677734375,
+      "logps/chosen": -167.0458984375,
+      "logps/rejected": -188.22262573242188,
+      "loss": 1.9736,
+      "rewards/accuracies": 0.6666667461395264,
+      "rewards/chosen": -13.132657051086426,
+      "rewards/margins": 17.90899085998535,
+      "rewards/rejected": -31.041645050048828,
+      "step": 210
+    },
+    {
+      "epoch": 0.1726844583987441,
+      "grad_norm": 13.95805192206325,
+      "learning_rate": 4.920911573406924e-07,
+      "logits/chosen": 6353.7783203125,
+      "logits/rejected": 5411.5087890625,
+      "logps/chosen": -207.0021514892578,
+      "logps/rejected": -192.39125061035156,
+      "loss": 1.97,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -10.665520668029785,
+      "rewards/margins": 17.728992462158203,
+      "rewards/rejected": -28.39451026916504,
+      "step": 220
+    },
+    {
+      "epoch": 0.18053375196232338,
+      "grad_norm": 7.164170611764204,
+      "learning_rate": 4.902902206053098e-07,
+      "logits/chosen": 5817.7529296875,
+      "logits/rejected": 5253.7822265625,
+      "logps/chosen": -201.00804138183594,
+      "logps/rejected": -212.4803924560547,
+      "loss": 1.9743,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -13.669303894042969,
+      "rewards/margins": 19.043621063232422,
+      "rewards/rejected": -32.71292495727539,
+      "step": 230
+    },
+    {
+      "epoch": 0.18838304552590268,
+      "grad_norm": 11.660382561338869,
+      "learning_rate": 4.883087164434672e-07,
+      "logits/chosen": 5308.75634765625,
+      "logits/rejected": 4242.29345703125,
+      "logps/chosen": -174.8252716064453,
+      "logps/rejected": -180.3127899169922,
+      "loss": 1.9672,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -7.196226596832275,
+      "rewards/margins": 18.427143096923828,
+      "rewards/rejected": -25.623367309570312,
+      "step": 240
+    },
+    {
+      "epoch": 0.19623233908948196,
+      "grad_norm": 8.72617485657044,
+      "learning_rate": 4.861481338675183e-07,
+      "logits/chosen": 6269.2236328125,
+      "logits/rejected": 5571.205078125,
+      "logps/chosen": -180.53604125976562,
+      "logps/rejected": -221.07125854492188,
+      "loss": 1.9743,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -13.392184257507324,
+      "rewards/margins": 23.172420501708984,
+      "rewards/rejected": -36.564598083496094,
+      "step": 250
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 10.038046373183738,
+      "learning_rate": 4.838100964592904e-07,
+      "logits/chosen": 6411.8017578125,
+      "logits/rejected": 5188.3544921875,
+      "logps/chosen": -212.73208618164062,
+      "logps/rejected": -196.77479553222656,
+      "loss": 1.9814,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -13.01362419128418,
+      "rewards/margins": 17.537227630615234,
+      "rewards/rejected": -30.550851821899414,
+      "step": 260
+    },
+    {
+      "epoch": 0.2119309262166405,
+      "grad_norm": 7.978893418055898,
+      "learning_rate": 4.812963611500339e-07,
+      "logits/chosen": 6247.86376953125,
+      "logits/rejected": 6049.94140625,
+      "logps/chosen": -206.0583038330078,
+      "logps/rejected": -213.51162719726562,
+      "loss": 1.962,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -9.302484512329102,
+      "rewards/margins": 15.580082893371582,
+      "rewards/rejected": -24.882568359375,
+      "step": 270
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 18.46477187944741,
+      "learning_rate": 4.786088169001671e-07,
+      "logits/chosen": 5388.15673828125,
+      "logits/rejected": 4686.12939453125,
+      "logps/chosen": -176.19607543945312,
+      "logps/rejected": -213.16305541992188,
+      "loss": 1.9659,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -13.045190811157227,
+      "rewards/margins": 30.816421508789062,
+      "rewards/rejected": -43.861610412597656,
+      "step": 280
+    },
+    {
+      "epoch": 0.22762951334379905,
+      "grad_norm": 16.83181121684455,
+      "learning_rate": 4.7574948327980567e-07,
+      "logits/chosen": 7499.02490234375,
+      "logits/rejected": 5559.24609375,
+      "logps/chosen": -246.99514770507812,
+      "logps/rejected": -226.33572387695312,
+      "loss": 1.9613,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -9.966670036315918,
+      "rewards/margins": 33.853336334228516,
+      "rewards/rejected": -43.81999969482422,
+      "step": 290
+    },
+    {
+      "epoch": 0.23547880690737832,
+      "grad_norm": 10.713215982695514,
+      "learning_rate": 4.727205089511466e-07,
+      "logits/chosen": 5454.79150390625,
+      "logits/rejected": 5429.51171875,
+      "logps/chosen": -181.81573486328125,
+      "logps/rejected": -206.89437866210938,
+      "loss": 1.975,
+      "rewards/accuracies": 0.6833333969116211,
+      "rewards/chosen": -14.343295097351074,
+      "rewards/margins": 22.364656448364258,
+      "rewards/rejected": -36.707950592041016,
+      "step": 300
+    },
+    {
+      "epoch": 0.24332810047095763,
+      "grad_norm": 10.320663018292882,
+      "learning_rate": 4.6952417005384247e-07,
+      "logits/chosen": 6112.76806640625,
+      "logits/rejected": 5453.38134765625,
+      "logps/chosen": -185.7081298828125,
+      "logps/rejected": -200.83535766601562,
+      "loss": 1.9697,
+      "rewards/accuracies": 0.7666667699813843,
+      "rewards/chosen": -8.127434730529785,
+      "rewards/margins": 17.2396297454834,
+      "rewards/rejected": -25.367061614990234,
+      "step": 310
+    },
+    {
+      "epoch": 0.25117739403453687,
+      "grad_norm": 10.476570210269244,
+      "learning_rate": 4.661628684945851e-07,
+      "logits/chosen": 6115.5517578125,
+      "logits/rejected": 5302.81689453125,
+      "logps/chosen": -209.9392852783203,
+      "logps/rejected": -239.3898468017578,
+      "loss": 1.964,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -8.882265090942383,
+      "rewards/margins": 28.489694595336914,
+      "rewards/rejected": -37.37196350097656,
+      "step": 320
+    },
+    {
+      "epoch": 0.25902668759811615,
+      "grad_norm": 8.453410137621447,
+      "learning_rate": 4.626391301421782e-07,
+      "logits/chosen": 5915.05224609375,
+      "logits/rejected": 5387.32177734375,
+      "logps/chosen": -203.82455444335938,
+      "logps/rejected": -205.4024200439453,
+      "loss": 1.9754,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": -9.371356964111328,
+      "rewards/margins": 18.708255767822266,
+      "rewards/rejected": -28.079614639282227,
+      "step": 330
+    },
+    {
+      "epoch": 0.2668759811616955,
+      "grad_norm": 7.101482635499888,
+      "learning_rate": 4.5895560292945996e-07,
+      "logits/chosen": 6163.81689453125,
+      "logits/rejected": 6304.29736328125,
+      "logps/chosen": -200.20118713378906,
+      "logps/rejected": -244.84848022460938,
+      "loss": 1.9674,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -6.342929363250732,
+      "rewards/margins": 18.13802719116211,
+      "rewards/rejected": -24.480958938598633,
+      "step": 340
+    },
+    {
+      "epoch": 0.27472527472527475,
+      "grad_norm": 22.517967387414878,
+      "learning_rate": 4.5511505486349865e-07,
+      "logits/chosen": 6512.6396484375,
+      "logits/rejected": 5911.80859375,
+      "logps/chosen": -203.82406616210938,
+      "logps/rejected": -247.0866241455078,
+      "loss": 1.9653,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -8.998370170593262,
+      "rewards/margins": 31.266225814819336,
+      "rewards/rejected": -40.26459503173828,
+      "step": 350
+    },
+    {
+      "epoch": 0.282574568288854,
+      "grad_norm": 10.024372865307708,
+      "learning_rate": 4.5112037194555876e-07,
+      "logits/chosen": 5994.025390625,
+      "logits/rejected": 5905.3828125,
+      "logps/chosen": -195.99481201171875,
+      "logps/rejected": -248.48153686523438,
+      "loss": 1.9671,
+      "rewards/accuracies": 0.7249999642372131,
+      "rewards/chosen": -18.07135772705078,
+      "rewards/margins": 31.128345489501953,
+      "rewards/rejected": -49.199703216552734,
+      "step": 360
+    },
+    {
+      "epoch": 0.2904238618524333,
+      "grad_norm": 9.19113626070318,
+      "learning_rate": 4.4697455600239863e-07,
+      "logits/chosen": 5450.50537109375,
+      "logits/rejected": 5144.671875,
+      "logps/chosen": -196.91354370117188,
+      "logps/rejected": -200.369873046875,
+      "loss": 1.9767,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -12.49148941040039,
+      "rewards/margins": 19.807308197021484,
+      "rewards/rejected": -32.29880142211914,
+      "step": 370
+    },
+    {
+      "epoch": 0.29827315541601257,
+      "grad_norm": 16.222088593597523,
+      "learning_rate": 4.426807224305315e-07,
+      "logits/chosen": 6513.00927734375,
+      "logits/rejected": 5406.20361328125,
+      "logps/chosen": -236.3499298095703,
+      "logps/rejected": -216.02804565429688,
+      "loss": 1.9675,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -8.00889778137207,
+      "rewards/margins": 25.009592056274414,
+      "rewards/rejected": -33.01848602294922,
+      "step": 380
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 16.753657487210614,
+      "learning_rate": 4.3824209785514326e-07,
+      "logits/chosen": 6674.41259765625,
+      "logits/rejected": 5131.07373046875,
+      "logps/chosen": -222.05276489257812,
+      "logps/rejected": -223.5919647216797,
+      "loss": 1.9553,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -6.559300899505615,
+      "rewards/margins": 37.17955780029297,
+      "rewards/rejected": -43.73885726928711,
+      "step": 390
+    },
+    {
+      "epoch": 0.3139717425431711,
+      "grad_norm": 9.085445983363275,
+      "learning_rate": 4.3366201770542687e-07,
+      "logits/chosen": 5777.0849609375,
+      "logits/rejected": 5671.5537109375,
+      "logps/chosen": -201.79702758789062,
+      "logps/rejected": -225.7125701904297,
+      "loss": 1.9761,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -11.008450508117676,
+      "rewards/margins": 25.964609146118164,
+      "rewards/rejected": -36.973060607910156,
+      "step": 400
+    },
+    {
+      "epoch": 0.3218210361067504,
+      "grad_norm": 11.33832444227533,
+      "learning_rate": 4.2894392370815567e-07,
+      "logits/chosen": 6256.8134765625,
+      "logits/rejected": 5594.1708984375,
+      "logps/chosen": -223.0230712890625,
+      "logps/rejected": -257.01385498046875,
+      "loss": 1.9476,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -10.536191940307617,
+      "rewards/margins": 38.025299072265625,
+      "rewards/rejected": -48.561485290527344,
+      "step": 410
+    },
+    {
+      "epoch": 0.32967032967032966,
+      "grad_norm": 16.273251635067584,
+      "learning_rate": 4.2409136130137845e-07,
+      "logits/chosen": 5923.02880859375,
+      "logits/rejected": 5376.9443359375,
+      "logps/chosen": -220.4603729248047,
+      "logps/rejected": -229.0534210205078,
+      "loss": 1.969,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -16.430438995361328,
+      "rewards/margins": 31.381549835205078,
+      "rewards/rejected": -47.81198501586914,
+      "step": 420
+    },
+    {
+      "epoch": 0.33751962323390894,
+      "grad_norm": 11.151359651562395,
+      "learning_rate": 4.1910797697018017e-07,
+      "logits/chosen": 5696.1357421875,
+      "logits/rejected": 4776.5791015625,
+      "logps/chosen": -192.7012939453125,
+      "logps/rejected": -203.29515075683594,
+      "loss": 1.9619,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -12.956321716308594,
+      "rewards/margins": 29.105701446533203,
+      "rewards/rejected": -42.06201934814453,
+      "step": 430
+    },
+    {
+      "epoch": 0.3453689167974882,
+      "grad_norm": 15.676627010168398,
+      "learning_rate": 4.1399751550651084e-07,
+      "logits/chosen": 6032.6103515625,
+      "logits/rejected": 5975.65869140625,
+      "logps/chosen": -194.45022583007812,
+      "logps/rejected": -232.76809692382812,
+      "loss": 1.9601,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -12.056891441345215,
+      "rewards/margins": 29.027606964111328,
+      "rewards/rejected": -41.08449935913086,
+      "step": 440
+    },
+    {
+      "epoch": 0.3532182103610675,
+      "grad_norm": 11.418135496524267,
+      "learning_rate": 4.087638171951401e-07,
+      "logits/chosen": 6920.4697265625,
+      "logits/rejected": 5017.2001953125,
+      "logps/chosen": -218.02651977539062,
+      "logps/rejected": -215.5140838623047,
+      "loss": 1.9654,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -9.257742881774902,
+      "rewards/margins": 43.26369857788086,
+      "rewards/rejected": -52.52144241333008,
+      "step": 450
+    },
+    {
+      "epoch": 0.36106750392464676,
+      "grad_norm": 9.738474609851922,
+      "learning_rate": 4.034108149278543e-07,
+      "logits/chosen": 7102.1494140625,
+      "logits/rejected": 5567.33251953125,
+      "logps/chosen": -262.5325622558594,
+      "logps/rejected": -226.304931640625,
+      "loss": 1.9647,
+      "rewards/accuracies": 0.7166666388511658,
+      "rewards/chosen": -12.100336074829102,
+      "rewards/margins": 23.9965763092041,
+      "rewards/rejected": -36.09691619873047,
+      "step": 460
+    },
+    {
+      "epoch": 0.36891679748822603,
+      "grad_norm": 16.944485993230334,
+      "learning_rate": 3.979425312480629e-07,
+      "logits/chosen": 6121.8251953125,
+      "logits/rejected": 5385.27978515625,
+      "logps/chosen": -226.22708129882812,
+      "logps/rejected": -247.5476531982422,
+      "loss": 1.961,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -13.962315559387207,
+      "rewards/margins": 31.019052505493164,
+      "rewards/rejected": -44.98136520385742,
+      "step": 470
+    },
+    {
+      "epoch": 0.37676609105180536,
+      "grad_norm": 10.061154653659795,
+      "learning_rate": 3.923630753280357e-07,
+      "logits/chosen": 6582.51708984375,
+      "logits/rejected": 5718.14208984375,
+      "logps/chosen": -220.9097900390625,
+      "logps/rejected": -222.513916015625,
+      "loss": 1.9678,
+      "rewards/accuracies": 0.8000000715255737,
+      "rewards/chosen": -13.514605522155762,
+      "rewards/margins": 34.60355758666992,
+      "rewards/rejected": -48.118160247802734,
+      "step": 480
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 9.952729544567205,
+      "learning_rate": 3.866766398810424e-07,
+      "logits/chosen": 6168.904296875,
+      "logits/rejected": 5932.04833984375,
+      "logps/chosen": -181.2738494873047,
+      "logps/rejected": -238.46578979492188,
+      "loss": 1.9539,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -4.665351390838623,
+      "rewards/margins": 31.776134490966797,
+      "rewards/rejected": -36.44148635864258,
+      "step": 490
+    },
+    {
+      "epoch": 0.3924646781789639,
+      "grad_norm": 10.886191142069716,
+      "learning_rate": 3.8088749801071496e-07,
+      "logits/chosen": 6751.1181640625,
+      "logits/rejected": 5237.1748046875,
+      "logps/chosen": -239.8447723388672,
+      "logps/rejected": -258.9305725097656,
+      "loss": 1.9645,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": -17.89109230041504,
+      "rewards/margins": 38.52326202392578,
+      "rewards/rejected": -56.41435623168945,
+      "step": 500
+    },
+    {
+      "epoch": 0.4003139717425432,
+      "grad_norm": 12.12571996214556,
+      "learning_rate": 3.75e-07,
+      "logits/chosen": 5390.6787109375,
+      "logits/rejected": 4790.146484375,
+      "logps/chosen": -199.76528930664062,
+      "logps/rejected": -217.97457885742188,
+      "loss": 1.9639,
+      "rewards/accuracies": 0.8166666030883789,
+      "rewards/chosen": -10.282281875610352,
+      "rewards/margins": 41.32698440551758,
+      "rewards/rejected": -51.60927200317383,
+      "step": 510
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 9.519450563259452,
+      "learning_rate": 3.6901857004211443e-07,
+      "logits/chosen": 5713.3515625,
+      "logits/rejected": 5326.962890625,
+      "logps/chosen": -212.322998046875,
+      "logps/rejected": -235.4215850830078,
+      "loss": 1.9753,
+      "rewards/accuracies": 0.6916667222976685,
+      "rewards/chosen": -13.85698127746582,
+      "rewards/margins": 25.776592254638672,
+      "rewards/rejected": -39.63357925415039,
+      "step": 520
+    },
+    {
+      "epoch": 0.41601255886970173,
+      "grad_norm": 9.888104468321709,
+      "learning_rate": 3.6294770291596076e-07,
+      "logits/chosen": 6448.71337890625,
+      "logits/rejected": 5332.93701171875,
+      "logps/chosen": -219.8802947998047,
+      "logps/rejected": -227.52792358398438,
+      "loss": 1.9559,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -6.957555294036865,
+      "rewards/margins": 21.810047149658203,
+      "rewards/rejected": -28.767602920532227,
+      "step": 530
+    },
+    {
+      "epoch": 0.423861852433281,
+      "grad_norm": 32.92673172258904,
+      "learning_rate": 3.5679196060850034e-07,
+      "logits/chosen": 6134.5771484375,
+      "logits/rejected": 5512.7548828125,
+      "logps/chosen": -224.2685089111328,
+      "logps/rejected": -235.88308715820312,
+      "loss": 1.9648,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -13.450671195983887,
+      "rewards/margins": 34.19359588623047,
+      "rewards/rejected": -47.64427185058594,
+      "step": 540
+    },
+    {
+      "epoch": 0.4317111459968603,
+      "grad_norm": 10.505039462285955,
+      "learning_rate": 3.505559688866229e-07,
+      "logits/chosen": 5928.0751953125,
+      "logits/rejected": 5549.6640625,
+      "logps/chosen": -229.20504760742188,
+      "logps/rejected": -271.86517333984375,
+      "loss": 1.9554,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -14.464628219604492,
+      "rewards/margins": 32.33644485473633,
+      "rewards/rejected": -46.80107498168945,
+      "step": 550
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 10.28700128076687,
+      "learning_rate": 3.4424441382108826e-07,
+      "logits/chosen": 5985.54833984375,
+      "logits/rejected": 5623.6748046875,
+      "logps/chosen": -218.4139862060547,
+      "logps/rejected": -238.92288208007812,
+      "loss": 1.9712,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": -15.138700485229492,
+      "rewards/margins": 30.574970245361328,
+      "rewards/rejected": -45.71367263793945,
+      "step": 560
+    },
+    {
+      "epoch": 0.4474097331240188,
+      "grad_norm": 15.423527438178777,
+      "learning_rate": 3.378620382651523e-07,
+      "logits/chosen": 6308.0498046875,
+      "logits/rejected": 5838.08056640625,
+      "logps/chosen": -258.34332275390625,
+      "logps/rejected": -273.0830383300781,
+      "loss": 1.9588,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -15.38349437713623,
+      "rewards/margins": 33.929012298583984,
+      "rewards/rejected": -49.3125114440918,
+      "step": 570
+    },
+    {
+      "epoch": 0.4552590266875981,
+      "grad_norm": 14.611083089156338,
+      "learning_rate": 3.314136382905234e-07,
+      "logits/chosen": 6261.64453125,
+      "logits/rejected": 5689.3505859375,
+      "logps/chosen": -222.60165405273438,
+      "logps/rejected": -264.10699462890625,
+      "loss": 1.9673,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -10.186196327209473,
+      "rewards/margins": 40.609474182128906,
+      "rewards/rejected": -50.79567337036133,
+      "step": 580
+    },
+    {
+      "epoch": 0.4631083202511774,
+      "grad_norm": 14.179147587086423,
+      "learning_rate": 3.249040595833274e-07,
+      "logits/chosen": 6810.31884765625,
+      "logits/rejected": 5779.87451171875,
+      "logps/chosen": -244.0528564453125,
+      "logps/rejected": -228.9059600830078,
+      "loss": 1.9497,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -12.326987266540527,
+      "rewards/margins": 37.720115661621094,
+      "rewards/rejected": -50.0471076965332,
+      "step": 590
+    },
+    {
+      "epoch": 0.47095761381475665,
+      "grad_norm": 19.155016516986336,
+      "learning_rate": 3.1833819380279023e-07,
+      "logits/chosen": 6452.5693359375,
+      "logits/rejected": 5529.4580078125,
+      "logps/chosen": -190.16168212890625,
+      "logps/rejected": -239.14492797851562,
+      "loss": 1.9536,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -12.613371849060059,
+      "rewards/margins": 36.84527587890625,
+      "rewards/rejected": -49.458648681640625,
+      "step": 600
+    },
+    {
+      "epoch": 0.478806907378336,
+      "grad_norm": 13.224856834760333,
+      "learning_rate": 3.11720974905373e-07,
+      "logits/chosen": 6204.62841796875,
+      "logits/rejected": 5447.55419921875,
+      "logps/chosen": -216.75570678710938,
+      "logps/rejected": -233.86032104492188,
+      "loss": 1.9449,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -10.637582778930664,
+      "rewards/margins": 37.80018997192383,
+      "rewards/rejected": -48.437767028808594,
+      "step": 610
+    },
+    {
+      "epoch": 0.48665620094191525,
+      "grad_norm": 17.52069876117691,
+      "learning_rate": 3.0505737543712275e-07,
+      "logits/chosen": 5294.59375,
+      "logits/rejected": 4387.63818359375,
+      "logps/chosen": -196.4014129638672,
+      "logps/rejected": -210.00869750976562,
+      "loss": 1.9549,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -12.642759323120117,
+      "rewards/margins": 36.267051696777344,
+      "rewards/rejected": -48.909812927246094,
+      "step": 620
+    },
+    {
+      "epoch": 0.4945054945054945,
+      "grad_norm": 33.05264787102616,
+      "learning_rate": 2.9835240279702513e-07,
+      "logits/chosen": 6885.4189453125,
+      "logits/rejected": 5920.83056640625,
+      "logps/chosen": -251.9607696533203,
+      "logps/rejected": -256.430908203125,
+      "loss": 1.9577,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -9.144782066345215,
+      "rewards/margins": 53.038055419921875,
+      "rewards/rejected": -62.182838439941406,
+      "step": 630
+    },
+    {
+      "epoch": 0.5023547880690737,
+      "grad_norm": 13.271843782155607,
+      "learning_rate": 2.9161109547416667e-07,
+      "logits/chosen": 6548.42822265625,
+      "logits/rejected": 5635.82861328125,
+      "logps/chosen": -226.5624542236328,
+      "logps/rejected": -251.34622192382812,
+      "loss": 1.9503,
+      "rewards/accuracies": 0.6916666626930237,
+      "rewards/chosen": -15.800863265991211,
+      "rewards/margins": 21.036413192749023,
+      "rewards/rejected": -36.837284088134766,
+      "step": 640
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 15.831220822034595,
+      "learning_rate": 2.848385192615339e-07,
+      "logits/chosen": 5647.466796875,
+      "logits/rejected": 4650.84326171875,
+      "logps/chosen": -208.1371612548828,
+      "logps/rejected": -215.1590118408203,
+      "loss": 1.9581,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -11.797808647155762,
+      "rewards/margins": 34.633445739746094,
+      "rewards/rejected": -46.431251525878906,
+      "step": 650
+    },
+    {
+      "epoch": 0.5180533751962323,
+      "grad_norm": 11.97405793704744,
+      "learning_rate": 2.780397634492949e-07,
+      "logits/chosen": 6318.73193359375,
+      "logits/rejected": 5105.6806640625,
+      "logps/chosen": -228.73629760742188,
+      "logps/rejected": -247.58203125,
+      "loss": 1.9628,
+      "rewards/accuracies": 0.8166667222976685,
+      "rewards/chosen": -11.349790573120117,
+      "rewards/margins": 48.284786224365234,
+      "rewards/rejected": -59.63458251953125,
+      "step": 660
+    },
+    {
+      "epoch": 0.5259026687598116,
+      "grad_norm": 15.694525160199404,
+      "learning_rate": 2.71219937000424e-07,
+      "logits/chosen": 6305.85546875,
+      "logits/rejected": 5219.8154296875,
+      "logps/chosen": -218.81637573242188,
+      "logps/rejected": -233.28933715820312,
+      "loss": 1.9636,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -12.056918144226074,
+      "rewards/margins": 32.37800216674805,
+      "rewards/rejected": -44.4349250793457,
+      "step": 670
+    },
+    {
+      "epoch": 0.533751962323391,
+      "grad_norm": 12.2450633413355,
+      "learning_rate": 2.6438416471154273e-07,
+      "logits/chosen": 6118.7060546875,
+      "logits/rejected": 5147.07470703125,
+      "logps/chosen": -223.75503540039062,
+      "logps/rejected": -228.0189971923828,
+      "loss": 1.9541,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -10.093757629394531,
+      "rewards/margins": 38.698543548583984,
+      "rewards/rejected": -48.79230499267578,
+      "step": 680
+    },
+    {
+      "epoch": 0.5416012558869702,
+      "grad_norm": 13.662534533205077,
+      "learning_rate": 2.5753758336186326e-07,
+      "logits/chosen": 6057.73046875,
+      "logits/rejected": 5582.77783203125,
+      "logps/chosen": -225.1211700439453,
+      "logps/rejected": -271.24847412109375,
+      "loss": 1.9559,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -16.014719009399414,
+      "rewards/margins": 39.03708267211914,
+      "rewards/rejected": -55.051795959472656,
+      "step": 690
+    },
+    {
+      "epoch": 0.5494505494505495,
+      "grad_norm": 20.150978172477505,
+      "learning_rate": 2.5068533785312666e-07,
+      "logits/chosen": 5760.0908203125,
+      "logits/rejected": 5564.3642578125,
+      "logps/chosen": -206.0763702392578,
+      "logps/rejected": -243.00936889648438,
+      "loss": 1.9826,
+      "rewards/accuracies": 0.7333332896232605,
+      "rewards/chosen": -16.816057205200195,
+      "rewards/margins": 39.219337463378906,
+      "rewards/rejected": -56.03539276123047,
+      "step": 700
+    },
+    {
+      "epoch": 0.5572998430141287,
+      "grad_norm": 13.452123278177462,
+      "learning_rate": 2.4383257734343794e-07,
+      "logits/chosen": 5708.1435546875,
+      "logits/rejected": 5760.40869140625,
+      "logps/chosen": -205.77761840820312,
+      "logps/rejected": -244.1310577392578,
+      "loss": 1.956,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -11.866220474243164,
+      "rewards/margins": 29.644180297851562,
+      "rewards/rejected": -41.510398864746094,
+      "step": 710
+    },
+    {
+      "epoch": 0.565149136577708,
+      "grad_norm": 9.709598082836985,
+      "learning_rate": 2.3698445137790258e-07,
+      "logits/chosen": 6114.9091796875,
+      "logits/rejected": 5311.08251953125,
+      "logps/chosen": -227.6648406982422,
+      "logps/rejected": -236.38330078125,
+      "loss": 1.9662,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -8.66163158416748,
+      "rewards/margins": 27.956518173217773,
+      "rewards/rejected": -36.61814880371094,
+      "step": 720
+    },
+    {
+      "epoch": 0.5729984301412873,
+      "grad_norm": 12.868770235170873,
+      "learning_rate": 2.3014610601897157e-07,
+      "logits/chosen": 6644.2060546875,
+      "logits/rejected": 5136.859375,
+      "logps/chosen": -238.3865966796875,
+      "logps/rejected": -222.13784790039062,
+      "loss": 1.9514,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -13.240676879882812,
+      "rewards/margins": 33.82345199584961,
+      "rewards/rejected": -47.06413650512695,
+      "step": 730
+    },
+    {
+      "epoch": 0.5808477237048666,
+      "grad_norm": 15.41698862667205,
+      "learning_rate": 2.2332267997940513e-07,
+      "logits/chosen": 5527.283203125,
+      "logits/rejected": 4719.14013671875,
+      "logps/chosen": -203.3306427001953,
+      "logps/rejected": -216.73959350585938,
+      "loss": 1.9527,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -10.906192779541016,
+      "rewards/margins": 43.1873664855957,
+      "rewards/rejected": -54.09355545043945,
+      "step": 740
+    },
+    {
+      "epoch": 0.5886970172684458,
+      "grad_norm": 13.318035652689497,
+      "learning_rate": 2.1651930076075723e-07,
+      "logits/chosen": 6021.62890625,
+      "logits/rejected": 5484.7626953125,
+      "logps/chosen": -193.93162536621094,
+      "logps/rejected": -213.35128784179688,
+      "loss": 1.9612,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -13.50567626953125,
+      "rewards/margins": 32.751338958740234,
+      "rewards/rejected": -46.25701141357422,
+      "step": 750
+    },
+    {
+      "epoch": 0.5965463108320251,
+      "grad_norm": 17.96255248447627,
+      "learning_rate": 2.0974108080028692e-07,
+      "logits/chosen": 6310.85986328125,
+      "logits/rejected": 5030.54736328125,
+      "logps/chosen": -213.32278442382812,
+      "logps/rejected": -214.3714599609375,
+      "loss": 1.9636,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -10.071836471557617,
+      "rewards/margins": 29.769107818603516,
+      "rewards/rejected": -39.8409423828125,
+      "step": 760
+    },
+    {
+      "epoch": 0.6043956043956044,
+      "grad_norm": 22.574869511207616,
+      "learning_rate": 2.0299311362918773e-07,
+      "logits/chosen": 6518.14404296875,
+      "logits/rejected": 5643.26220703125,
+      "logps/chosen": -245.22970581054688,
+      "logps/rejected": -276.74285888671875,
+      "loss": 1.9681,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -15.496047973632812,
+      "rewards/margins": 37.38671112060547,
+      "rewards/rejected": -52.88275909423828,
+      "step": 770
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 31.521005261418978,
+      "learning_rate": 1.962804700450265e-07,
+      "logits/chosen": 6350.6767578125,
+      "logits/rejected": 6074.388671875,
+      "logps/chosen": -227.0453643798828,
+      "logps/rejected": -277.8321838378906,
+      "loss": 1.9662,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -10.940030097961426,
+      "rewards/margins": 29.504467010498047,
+      "rewards/rejected": -40.44449996948242,
+      "step": 780
+    },
+    {
+      "epoch": 0.6200941915227629,
+      "grad_norm": 19.737346143715538,
+      "learning_rate": 1.8960819430126334e-07,
+      "logits/chosen": 5919.3037109375,
+      "logits/rejected": 5263.5703125,
+      "logps/chosen": -215.43441772460938,
+      "logps/rejected": -249.7850799560547,
+      "loss": 1.9556,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -17.30341148376465,
+      "rewards/margins": 43.883941650390625,
+      "rewards/rejected": -61.187347412109375,
+      "step": 790
+    },
+    {
+      "epoch": 0.6279434850863422,
+      "grad_norm": 18.29038936836771,
+      "learning_rate": 1.8298130031671972e-07,
+      "logits/chosen": 5920.49365234375,
+      "logits/rejected": 5215.0712890625,
+      "logps/chosen": -233.1874542236328,
+      "logps/rejected": -261.2085266113281,
+      "loss": 1.9726,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -16.46460723876953,
+      "rewards/margins": 32.04566192626953,
+      "rewards/rejected": -48.5102653503418,
+      "step": 800
+    },
+    {
+      "epoch": 0.6357927786499215,
+      "grad_norm": 12.137685601024057,
+      "learning_rate": 1.7640476790784075e-07,
+      "logits/chosen": 5467.83251953125,
+      "logits/rejected": 4939.65087890625,
+      "logps/chosen": -212.20767211914062,
+      "logps/rejected": -267.3034973144531,
+      "loss": 1.9569,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -9.752274513244629,
+      "rewards/margins": 36.25393295288086,
+      "rewards/rejected": -46.00621032714844,
+      "step": 810
+    },
+    {
+      "epoch": 0.6436420722135008,
+      "grad_norm": 13.63770692303666,
+      "learning_rate": 1.6988353904658492e-07,
+      "logits/chosen": 5939.91552734375,
+      "logits/rejected": 4631.35205078125,
+      "logps/chosen": -229.2455291748047,
+      "logps/rejected": -209.6826629638672,
+      "loss": 1.9476,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -8.030985832214355,
+      "rewards/margins": 32.963321685791016,
+      "rewards/rejected": -40.99430465698242,
+      "step": 820
+    },
+    {
+      "epoch": 0.6514913657770801,
+      "grad_norm": 35.3592513671855,
+      "learning_rate": 1.634225141467513e-07,
+      "logits/chosen": 5885.0146484375,
+      "logits/rejected": 5291.1865234375,
+      "logps/chosen": -221.3533172607422,
+      "logps/rejected": -254.42501831054688,
+      "loss": 1.9561,
+      "rewards/accuracies": 0.73333340883255,
+      "rewards/chosen": -17.167299270629883,
+      "rewards/margins": 44.80288314819336,
+      "rewards/rejected": -61.97017288208008,
+      "step": 830
+    },
+    {
+      "epoch": 0.6593406593406593,
+      "grad_norm": 10.761005849291488,
+      "learning_rate": 1.570265483815364e-07,
+      "logits/chosen": 6429.474609375,
+      "logits/rejected": 5307.4501953125,
+      "logps/chosen": -245.8719024658203,
+      "logps/rejected": -261.5577087402344,
+      "loss": 1.9591,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": -18.54207420349121,
+      "rewards/margins": 30.222482681274414,
+      "rewards/rejected": -48.764556884765625,
+      "step": 840
+    },
+    {
+      "epoch": 0.6671899529042387,
+      "grad_norm": 16.29666584290201,
+      "learning_rate": 1.5070044803508691e-07,
+      "logits/chosen": 5947.8916015625,
+      "logits/rejected": 5381.05810546875,
+      "logps/chosen": -227.6597900390625,
+      "logps/rejected": -256.93426513671875,
+      "loss": 1.9444,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -12.182321548461914,
+      "rewards/margins": 44.29661560058594,
+      "rewards/rejected": -56.47894287109375,
+      "step": 850
+    },
+    {
+      "epoch": 0.6750392464678179,
+      "grad_norm": 14.229262245757536,
+      "learning_rate": 1.444489668907914e-07,
+      "logits/chosen": 6413.134765625,
+      "logits/rejected": 5485.0712890625,
+      "logps/chosen": -259.97039794921875,
+      "logps/rejected": -254.68661499023438,
+      "loss": 1.9651,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -12.199740409851074,
+      "rewards/margins": 39.80502700805664,
+      "rewards/rejected": -52.00476837158203,
+      "step": 860
+    },
+    {
+      "epoch": 0.6828885400313972,
+      "grad_norm": 14.985139051030577,
+      "learning_rate": 1.3827680265902232e-07,
+      "logits/chosen": 6375.4150390625,
+      "logits/rejected": 5318.18603515625,
+      "logps/chosen": -241.5561065673828,
+      "logps/rejected": -245.6100616455078,
+      "loss": 1.9577,
+      "rewards/accuracies": 0.7750000357627869,
+      "rewards/chosen": -11.459368705749512,
+      "rewards/margins": 33.461753845214844,
+      "rewards/rejected": -44.92112731933594,
+      "step": 870
+    },
+    {
+      "epoch": 0.6907378335949764,
+      "grad_norm": 21.012999888781128,
+      "learning_rate": 1.3218859344701632e-07,
+      "logits/chosen": 5609.716796875,
+      "logits/rejected": 5388.8818359375,
+      "logps/chosen": -221.8362579345703,
+      "logps/rejected": -279.399658203125,
+      "loss": 1.9613,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -11.325273513793945,
+      "rewards/margins": 36.48521423339844,
+      "rewards/rejected": -47.81048583984375,
+      "step": 880
+    },
+    {
+      "epoch": 0.6985871271585558,
+      "grad_norm": 16.069902059846896,
+      "learning_rate": 1.2618891427354172e-07,
+      "logits/chosen": 6615.9248046875,
+      "logits/rejected": 5418.08447265625,
+      "logps/chosen": -268.32244873046875,
+      "logps/rejected": -266.2985534667969,
+      "loss": 1.9596,
+      "rewards/accuracies": 0.7999999523162842,
+      "rewards/chosen": -10.72636890411377,
+      "rewards/margins": 43.791648864746094,
+      "rewards/rejected": -54.51801681518555,
+      "step": 890
+    },
+    {
+      "epoch": 0.706436420722135,
+      "grad_norm": 14.83296947009343,
+      "learning_rate": 1.202822736309758e-07,
+      "logits/chosen": 5605.28662109375,
+      "logits/rejected": 5226.92236328125,
+      "logps/chosen": -214.8007049560547,
+      "logps/rejected": -256.61541748046875,
+      "loss": 1.9601,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -10.451518058776855,
+      "rewards/margins": 35.73381805419922,
+      "rewards/rejected": -46.185333251953125,
+      "step": 900
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 16.04357761307859,
+      "learning_rate": 1.1447311009737299e-07,
+      "logits/chosen": 5512.8681640625,
+      "logits/rejected": 5264.71142578125,
+      "logps/chosen": -220.86276245117188,
+      "logps/rejected": -260.4016418457031,
+      "loss": 1.9546,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -12.636472702026367,
+      "rewards/margins": 39.836666107177734,
+      "rewards/rejected": -52.47313690185547,
+      "step": 910
+    },
+    {
+      "epoch": 0.7221350078492935,
+      "grad_norm": 11.14000447509858,
+      "learning_rate": 1.0876578900107053e-07,
+      "logits/chosen": 6096.97314453125,
+      "logits/rejected": 5090.04052734375,
+      "logps/chosen": -245.5460968017578,
+      "logps/rejected": -248.48770141601562,
+      "loss": 1.9524,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -13.124479293823242,
+      "rewards/margins": 37.220909118652344,
+      "rewards/rejected": -50.34539031982422,
+      "step": 920
+    },
+    {
+      "epoch": 0.7299843014128728,
+      "grad_norm": 15.02248631232516,
+      "learning_rate": 1.0316459914033793e-07,
+      "logits/chosen": 6012.04833984375,
+      "logits/rejected": 4572.67333984375,
+      "logps/chosen": -253.6759796142578,
+      "logps/rejected": -244.62939453125,
+      "loss": 1.9584,
+      "rewards/accuracies": 0.7499999403953552,
+      "rewards/chosen": -17.687047958374023,
+      "rewards/margins": 41.01814651489258,
+      "rewards/rejected": -58.70519256591797,
+      "step": 930
+    },
+    {
+      "epoch": 0.7378335949764521,
+      "grad_norm": 14.78768614756301,
+      "learning_rate": 9.767374956053584e-08,
+      "logits/chosen": 5824.52392578125,
+      "logits/rejected": 5130.29150390625,
+      "logps/chosen": -231.50732421875,
+      "logps/rejected": -265.863525390625,
+      "loss": 1.9506,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -13.213656425476074,
+      "rewards/margins": 47.669952392578125,
+      "rewards/rejected": -60.88360595703125,
+      "step": 940
+    },
+    {
+      "epoch": 0.7456828885400314,
+      "grad_norm": 22.1690955607781,
+      "learning_rate": 9.229736639120561e-08,
+      "logits/chosen": 5999.9892578125,
+      "logits/rejected": 5568.5703125,
+      "logps/chosen": -230.053955078125,
+      "logps/rejected": -253.02633666992188,
+      "loss": 1.9589,
+      "rewards/accuracies": 0.7833333015441895,
+      "rewards/chosen": -12.252751350402832,
+      "rewards/margins": 26.61910057067871,
+      "rewards/rejected": -38.871849060058594,
+      "step": 950
+    },
+    {
+      "epoch": 0.7535321821036107,
+      "grad_norm": 17.03053961858823,
+      "learning_rate": 8.70394897454659e-08,
+      "logits/chosen": 5853.4912109375,
+      "logits/rejected": 5239.51708984375,
+      "logps/chosen": -227.2183380126953,
+      "logps/rejected": -253.36898803710938,
+      "loss": 1.9478,
+      "rewards/accuracies": 0.7916666865348816,
+      "rewards/chosen": -8.789916038513184,
+      "rewards/margins": 42.10274887084961,
+      "rewards/rejected": -50.892677307128906,
+      "step": 960
+    },
+    {
+      "epoch": 0.7613814756671899,
+      "grad_norm": 24.752863800000334,
+      "learning_rate": 8.19040706840472e-08,
+      "logits/chosen": 5959.28515625,
+      "logits/rejected": 5025.02099609375,
+      "logps/chosen": -251.1478729248047,
+      "logps/rejected": -268.1574401855469,
+      "loss": 1.9401,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -10.927900314331055,
+      "rewards/margins": 50.53899383544922,
+      "rewards/rejected": -61.46689987182617,
+      "step": 970
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 16.610566886947357,
+      "learning_rate": 7.689496824624525e-08,
+      "logits/chosen": 5662.68359375,
+      "logits/rejected": 4593.669921875,
+      "logps/chosen": -239.620849609375,
+      "logps/rejected": -265.27178955078125,
+      "loss": 1.9424,
+      "rewards/accuracies": 0.8083332777023315,
+      "rewards/chosen": -10.80424690246582,
+      "rewards/margins": 63.973960876464844,
+      "rewards/rejected": -74.77821350097656,
+      "step": 980
+    },
+    {
+      "epoch": 0.7770800627943485,
+      "grad_norm": 36.937457019710536,
+      "learning_rate": 7.201594655002458e-08,
+      "logits/chosen": 5990.30712890625,
+      "logits/rejected": 5043.2490234375,
+      "logps/chosen": -240.4677734375,
+      "logps/rejected": -260.95574951171875,
+      "loss": 1.9499,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -14.572827339172363,
+      "rewards/margins": 52.31321334838867,
+      "rewards/rejected": -66.88603973388672,
+      "step": 990
+    },
+    {
+      "epoch": 0.7849293563579278,
+      "grad_norm": 23.03062466270963,
+      "learning_rate": 6.727067196345099e-08,
+      "logits/chosen": 5678.6806640625,
+      "logits/rejected": 4839.29931640625,
+      "logps/chosen": -227.02432250976562,
+      "logps/rejected": -228.1048126220703,
+      "loss": 1.9563,
+      "rewards/accuracies": 0.6916666626930237,
+      "rewards/chosen": -13.268468856811523,
+      "rewards/margins": 34.491050720214844,
+      "rewards/rejected": -47.759521484375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.792778649921507,
+      "grad_norm": 14.87512248096038,
+      "learning_rate": 6.26627103495786e-08,
+      "logits/chosen": 5860.2373046875,
+      "logits/rejected": 4920.7861328125,
+      "logps/chosen": -224.3702850341797,
+      "logps/rejected": -244.62551879882812,
+      "loss": 1.9538,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -9.661078453063965,
+      "rewards/margins": 43.53081512451172,
+      "rewards/rejected": -53.19189453125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8006279434850864,
+      "grad_norm": 14.748532824208521,
+      "learning_rate": 5.8195524386862374e-08,
+      "logits/chosen": 5948.0859375,
+      "logits/rejected": 5325.62939453125,
+      "logps/chosen": -256.8372802734375,
+      "logps/rejected": -279.39373779296875,
+      "loss": 1.9608,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -8.658674240112305,
+      "rewards/margins": 44.65437316894531,
+      "rewards/rejected": -53.31304931640625,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8084772370486656,
+      "grad_norm": 13.111496123331063,
+      "learning_rate": 5.38724709671092e-08,
+      "logits/chosen": 6350.22802734375,
+      "logits/rejected": 6027.82177734375,
+      "logps/chosen": -243.10403442382812,
+      "logps/rejected": -286.2555847167969,
+      "loss": 1.95,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": -11.635639190673828,
+      "rewards/margins": 41.500667572021484,
+      "rewards/rejected": -53.13630294799805,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 13.785799458642654,
+      "learning_rate": 4.969679867292276e-08,
+      "logits/chosen": 5649.2197265625,
+      "logits/rejected": 5181.4765625,
+      "logps/chosen": -237.51126098632812,
+      "logps/rejected": -271.2793273925781,
+      "loss": 1.95,
+      "rewards/accuracies": 0.7000000476837158,
+      "rewards/chosen": -17.409549713134766,
+      "rewards/margins": 44.685813903808594,
+      "rewards/rejected": -62.095359802246094,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8241758241758241,
+      "grad_norm": 18.785044476818584,
+      "learning_rate": 4.5671645336537416e-08,
+      "logits/chosen": 5704.8623046875,
+      "logits/rejected": 5225.52587890625,
+      "logps/chosen": -251.41500854492188,
+      "logps/rejected": -279.2231750488281,
+      "loss": 1.9535,
+      "rewards/accuracies": 0.73333340883255,
+      "rewards/chosen": -13.934377670288086,
+      "rewards/margins": 49.494422912597656,
+      "rewards/rejected": -63.428802490234375,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8320251177394035,
+      "grad_norm": 26.490352891661313,
+      "learning_rate": 4.180003568187776e-08,
+      "logits/chosen": 7039.8828125,
+      "logits/rejected": 5571.68212890625,
+      "logps/chosen": -277.3167419433594,
+      "logps/rejected": -269.80999755859375,
+      "loss": 1.9639,
+      "rewards/accuracies": 0.6666666865348816,
+      "rewards/chosen": -16.329357147216797,
+      "rewards/margins": 33.44147491455078,
+      "rewards/rejected": -49.770835876464844,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8398744113029827,
+      "grad_norm": 22.94047462012029,
+      "learning_rate": 3.8084879051612144e-08,
+      "logits/chosen": 5870.64013671875,
+      "logits/rejected": 5412.8837890625,
+      "logps/chosen": -234.2925262451172,
+      "logps/rejected": -246.66885375976562,
+      "loss": 1.953,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": -9.04952335357666,
+      "rewards/margins": 44.45494842529297,
+      "rewards/rejected": -53.50446701049805,
+      "step": 1070
+    },
+    {
+      "epoch": 0.847723704866562,
+      "grad_norm": 15.970389728332213,
+      "learning_rate": 3.452896722091128e-08,
+      "logits/chosen": 6428.0244140625,
+      "logits/rejected": 5009.7216796875,
+      "logps/chosen": -274.9081726074219,
+      "logps/rejected": -264.4786376953125,
+      "loss": 1.9422,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -8.338837623596191,
+      "rewards/margins": 55.159873962402344,
+      "rewards/rejected": -63.49870681762695,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8555729984301413,
+      "grad_norm": 18.198254677065798,
+      "learning_rate": 3.11349722995527e-08,
+      "logits/chosen": 6511.92822265625,
+      "logits/rejected": 4918.216796875,
+      "logps/chosen": -242.1095733642578,
+      "logps/rejected": -269.7752990722656,
+      "loss": 1.9586,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -14.634966850280762,
+      "rewards/margins": 42.25577926635742,
+      "rewards/rejected": -56.8907470703125,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8634222919937206,
+      "grad_norm": 16.804338867644905,
+      "learning_rate": 2.7905444723949762e-08,
+      "logits/chosen": 6285.3818359375,
+      "logits/rejected": 5230.830078125,
+      "logps/chosen": -252.6708526611328,
+      "logps/rejected": -250.3868408203125,
+      "loss": 1.9605,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -14.134493827819824,
+      "rewards/margins": 46.755001068115234,
+      "rewards/rejected": -60.889495849609375,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8712715855572999,
+      "grad_norm": 16.045778309961047,
+      "learning_rate": 2.484281134061142e-08,
+      "logits/chosen": 6644.92041015625,
+      "logits/rejected": 5396.99462890625,
+      "logps/chosen": -279.4850158691406,
+      "logps/rejected": -281.66839599609375,
+      "loss": 1.9534,
+      "rewards/accuracies": 0.7916666269302368,
+      "rewards/chosen": -14.871435165405273,
+      "rewards/margins": 44.52893829345703,
+      "rewards/rejected": -59.40037155151367,
+      "step": 1110
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 25.938670718923635,
+      "learning_rate": 2.194937358247506e-08,
+      "logits/chosen": 6502.3291015625,
+      "logits/rejected": 5317.71044921875,
+      "logps/chosen": -260.4866638183594,
+      "logps/rejected": -276.68133544921875,
+      "loss": 1.9533,
+      "rewards/accuracies": 0.7583333849906921,
+      "rewards/chosen": -15.346229553222656,
+      "rewards/margins": 44.5643310546875,
+      "rewards/rejected": -59.910552978515625,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8869701726844584,
+      "grad_norm": 24.916434094111068,
+      "learning_rate": 1.9227305739481612e-08,
+      "logits/chosen": 5917.8349609375,
+      "logits/rejected": 4701.77978515625,
+      "logps/chosen": -244.61825561523438,
+      "logps/rejected": -235.84878540039062,
+      "loss": 1.9449,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -9.836224555969238,
+      "rewards/margins": 45.78696823120117,
+      "rewards/rejected": -55.623199462890625,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8948194662480377,
+      "grad_norm": 14.382726209860957,
+      "learning_rate": 1.6678653324693787e-08,
+      "logits/chosen": 6504.939453125,
+      "logits/rejected": 5327.1845703125,
+      "logps/chosen": -270.0257873535156,
+      "logps/rejected": -271.5950622558594,
+      "loss": 1.9525,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -12.405012130737305,
+      "rewards/margins": 38.37703323364258,
+      "rewards/rejected": -50.78205108642578,
+      "step": 1140
+    },
+    {
+      "epoch": 0.902668759811617,
+      "grad_norm": 14.78835811924378,
+      "learning_rate": 1.4305331537183384e-08,
+      "logits/chosen": 5756.44970703125,
+      "logits/rejected": 5324.578125,
+      "logps/chosen": -238.2313690185547,
+      "logps/rejected": -266.89166259765625,
+      "loss": 1.9446,
+      "rewards/accuracies": 0.7500000596046448,
+      "rewards/chosen": -11.247991561889648,
+      "rewards/margins": 36.155738830566406,
+      "rewards/rejected": -47.40373229980469,
+      "step": 1150
+    },
+    {
+      "epoch": 0.9105180533751962,
+      "grad_norm": 23.21802503519393,
+      "learning_rate": 1.2109123822844653e-08,
+      "logits/chosen": 5926.2421875,
+      "logits/rejected": 4742.0224609375,
+      "logps/chosen": -244.4608917236328,
+      "logps/rejected": -248.4634552001953,
+      "loss": 1.9544,
+      "rewards/accuracies": 0.7333333492279053,
+      "rewards/chosen": -15.904090881347656,
+      "rewards/margins": 36.621253967285156,
+      "rewards/rejected": -52.52534103393555,
+      "step": 1160
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 22.422532860536233,
+      "learning_rate": 1.0091680534213387e-08,
+      "logits/chosen": 6495.7001953125,
+      "logits/rejected": 6269.51904296875,
+      "logps/chosen": -256.6058654785156,
+      "logps/rejected": -297.3378601074219,
+      "loss": 1.9577,
+      "rewards/accuracies": 0.7499999403953552,
+      "rewards/chosen": -13.657504081726074,
+      "rewards/margins": 36.93338394165039,
+      "rewards/rejected": -50.59088897705078,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9262166405023547,
+      "grad_norm": 19.603883456580654,
+      "learning_rate": 8.254517690300944e-09,
+      "logits/chosen": 5720.74365234375,
+      "logits/rejected": 5222.8046875,
+      "logps/chosen": -253.0874786376953,
+      "logps/rejected": -268.9738464355469,
+      "loss": 1.9593,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -13.141489028930664,
+      "rewards/margins": 39.01056671142578,
+      "rewards/rejected": -52.152061462402344,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9340659340659341,
+      "grad_norm": 17.033230362077003,
+      "learning_rate": 6.599015837372907e-09,
+      "logits/chosen": 6205.9697265625,
+      "logits/rejected": 5447.80859375,
+      "logps/chosen": -269.47576904296875,
+      "logps/rejected": -276.09552001953125,
+      "loss": 1.949,
+      "rewards/accuracies": 0.7083333730697632,
+      "rewards/chosen": -20.590267181396484,
+      "rewards/margins": 38.352821350097656,
+      "rewards/rejected": -58.943084716796875,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9419152276295133,
+      "grad_norm": 16.90413077812471,
+      "learning_rate": 5.126419011529992e-09,
+      "logits/chosen": 6419.7333984375,
+      "logits/rejected": 5498.9658203125,
+      "logps/chosen": -267.5433044433594,
+      "logps/rejected": -279.40057373046875,
+      "loss": 1.9507,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -11.881638526916504,
+      "rewards/margins": 48.85334014892578,
+      "rewards/rejected": -60.7349853515625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9497645211930926,
+      "grad_norm": 36.17870464463534,
+      "learning_rate": 3.837833803870177e-09,
+      "logits/chosen": 6007.43603515625,
+      "logits/rejected": 5288.4658203125,
+      "logps/chosen": -252.74148559570312,
+      "logps/rejected": -278.2850646972656,
+      "loss": 1.9559,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -12.555973052978516,
+      "rewards/margins": 47.52782440185547,
+      "rewards/rejected": -60.08379364013672,
+      "step": 1210
+    },
+    {
+      "epoch": 0.957613814756672,
+      "grad_norm": 16.61938883168565,
+      "learning_rate": 2.734228528934679e-09,
+      "logits/chosen": 7483.11962890625,
+      "logits/rejected": 5542.7509765625,
+      "logps/chosen": -313.7238464355469,
+      "logps/rejected": -300.87921142578125,
+      "loss": 1.9611,
+      "rewards/accuracies": 0.6833333969116211,
+      "rewards/chosen": -16.955432891845703,
+      "rewards/margins": 38.72659683227539,
+      "rewards/rejected": -55.682029724121094,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9654631083202512,
+      "grad_norm": 16.700922559123722,
+      "learning_rate": 1.8164324970625645e-09,
+      "logits/chosen": 6656.83984375,
+      "logits/rejected": 5284.20751953125,
+      "logps/chosen": -271.3492431640625,
+      "logps/rejected": -268.39617919921875,
+      "loss": 1.9547,
+      "rewards/accuracies": 0.7583333253860474,
+      "rewards/chosen": -10.767581939697266,
+      "rewards/margins": 44.63188171386719,
+      "rewards/rejected": -55.39946746826172,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9733124018838305,
+      "grad_norm": 14.035772074810767,
+      "learning_rate": 1.0851353912008642e-09,
+      "logits/chosen": 5738.1884765625,
+      "logits/rejected": 5294.599609375,
+      "logps/chosen": -250.1355438232422,
+      "logps/rejected": -292.23736572265625,
+      "loss": 1.9484,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -18.523162841796875,
+      "rewards/margins": 38.556339263916016,
+      "rewards/rejected": -57.079505920410156,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9811616954474097,
+      "grad_norm": 14.793452380633976,
+      "learning_rate": 5.408867486384471e-10,
+      "logits/chosen": 5854.9208984375,
+      "logits/rejected": 4967.2197265625,
+      "logps/chosen": -241.21725463867188,
+      "logps/rejected": -235.61495971679688,
+      "loss": 1.9573,
+      "rewards/accuracies": 0.7666666507720947,
+      "rewards/chosen": -10.9091215133667,
+      "rewards/margins": 35.27557373046875,
+      "rewards/rejected": -46.184696197509766,
+      "step": 1250
+    },
+    {
+      "epoch": 0.989010989010989,
+      "grad_norm": 16.612160087002778,
+      "learning_rate": 1.840955480532924e-10,
+      "logits/chosen": 5532.6669921875,
+      "logits/rejected": 5269.6572265625,
+      "logps/chosen": -246.49185180664062,
+      "logps/rejected": -263.04144287109375,
+      "loss": 1.9554,
+      "rewards/accuracies": 0.8083333969116211,
+      "rewards/chosen": -14.331242561340332,
+      "rewards/margins": 32.38512420654297,
+      "rewards/rejected": -46.71636962890625,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9968602825745683,
+      "grad_norm": 21.26616020403944,
+      "learning_rate": 1.502990218302247e-11,
+      "logits/chosen": 5808.15283203125,
+      "logits/rejected": 4749.75537109375,
+      "logps/chosen": -237.1238555908203,
+      "logps/rejected": -240.21200561523438,
+      "loss": 1.9474,
+      "rewards/accuracies": 0.7416666746139526,
+      "rewards/chosen": -12.649885177612305,
+      "rewards/margins": 41.257911682128906,
+      "rewards/rejected": -53.907798767089844,
+      "step": 1270
+    },
+    {
+      "epoch": 1.0,
+      "step": 1274,
+      "total_flos": 0.0,
+      "train_loss": 1.9640779633724146,
+      "train_runtime": 14760.7646,
+      "train_samples_per_second": 4.142,
+      "train_steps_per_second": 0.086
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1274,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}