Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- trl
+- orpo
+- generated_from_trainer
+model-index:
+- name: kaist-sft-mistral-OHP-15k-Stratified-1
+  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. -->
+
+# kaist-sft-mistral-OHP-15k-Stratified-1
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None 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-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.500827480283418,
+    "train_runtime": 21486.5219,
+    "train_samples": 14928,
+    "train_samples_per_second": 2.084,
+    "train_steps_per_second": 0.033
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a445abca289652034e50bf783a1fd71fc215ceb94f4270dd19897ffa044117b7
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a69397fea6049f1a676eb1503c9da67edf4c85812de2cf1333258b2b9d601a91
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd0a72c6394ace2a2189d33103702ebe2f7801e936f7bc8eb50fef6bc8e1018
+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 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.500827480283418,
+    "train_runtime": 21486.5219,
+    "train_samples": 14928,
+    "train_samples_per_second": 2.084,
+    "train_steps_per_second": 0.033
+}

trainer_state.json

@@ -0,0 +1,1272 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.996784565916399,
+  "eval_steps": 500,
+  "global_step": 699,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 16.25,
+      "learning_rate": 5.000000000000001e-07,
+      "log_odds_chosen": 0.06385541707277298,
+      "log_odds_ratio": -0.700367271900177,
+      "logits/chosen": -2.185523748397827,
+      "logits/rejected": -2.1816813945770264,
+      "logps/chosen": -0.9445573687553406,
+      "logps/rejected": -0.9744073748588562,
+      "loss": 0.7979,
+      "nll_loss": 0.7937018871307373,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 12.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "log_odds_chosen": 0.16918674111366272,
+      "log_odds_ratio": -0.6699416041374207,
+      "logits/chosen": -2.2384395599365234,
+      "logits/rejected": -2.15749454498291,
+      "logps/chosen": -0.7942744493484497,
+      "logps/rejected": -0.9024287462234497,
+      "loss": 0.7438,
+      "nll_loss": 0.7179641723632812,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 6.71875,
+      "learning_rate": 1.5e-06,
+      "log_odds_chosen": 0.006562241818755865,
+      "log_odds_ratio": -0.7472976446151733,
+      "logits/chosen": -2.2658329010009766,
+      "logits/rejected": -2.2255280017852783,
+      "logps/chosen": -0.7462302446365356,
+      "logps/rejected": -0.7592640519142151,
+      "loss": 0.6946,
+      "nll_loss": 0.709227442741394,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 6.53125,
+      "learning_rate": 2.0000000000000003e-06,
+      "log_odds_chosen": 0.130902498960495,
+      "log_odds_ratio": -0.696516215801239,
+      "logits/chosen": -2.31599497795105,
+      "logits/rejected": -2.197169780731201,
+      "logps/chosen": -0.6473785042762756,
+      "logps/rejected": -0.7054767608642578,
+      "loss": 0.6834,
+      "nll_loss": 0.6458895802497864,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 7.28125,
+      "learning_rate": 2.5e-06,
+      "log_odds_chosen": 0.10142650455236435,
+      "log_odds_ratio": -0.7053729891777039,
+      "logits/chosen": -2.2686123847961426,
+      "logits/rejected": -2.19942307472229,
+      "logps/chosen": -0.655845046043396,
+      "logps/rejected": -0.7169128656387329,
+      "loss": 0.6504,
+      "nll_loss": 0.6311678290367126,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.65625,
+      "learning_rate": 3e-06,
+      "log_odds_chosen": 0.04096098989248276,
+      "log_odds_ratio": -0.7439945936203003,
+      "logits/chosen": -2.2910470962524414,
+      "logits/rejected": -2.2046058177948,
+      "logps/chosen": -0.7029940485954285,
+      "logps/rejected": -0.7319748997688293,
+      "loss": 0.6785,
+      "nll_loss": 0.6775273084640503,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.375,
+      "learning_rate": 3.5e-06,
+      "log_odds_chosen": 0.039232559502124786,
+      "log_odds_ratio": -0.7308824062347412,
+      "logits/chosen": -2.2575812339782715,
+      "logits/rejected": -2.199249505996704,
+      "logps/chosen": -0.6514252424240112,
+      "logps/rejected": -0.6770638823509216,
+      "loss": 0.6408,
+      "nll_loss": 0.6384583711624146,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.0625,
+      "learning_rate": 4.000000000000001e-06,
+      "log_odds_chosen": 0.065470851957798,
+      "log_odds_ratio": -0.750912070274353,
+      "logits/chosen": -2.23573637008667,
+      "logits/rejected": -2.2267823219299316,
+      "logps/chosen": -0.694416344165802,
+      "logps/rejected": -0.7376698851585388,
+      "loss": 0.6678,
+      "nll_loss": 0.6970995664596558,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 7.4375,
+      "learning_rate": 4.5e-06,
+      "log_odds_chosen": 0.18219563364982605,
+      "log_odds_ratio": -0.6834715604782104,
+      "logits/chosen": -2.3221395015716553,
+      "logits/rejected": -2.2302544116973877,
+      "logps/chosen": -0.6259569525718689,
+      "logps/rejected": -0.7380796074867249,
+      "loss": 0.6328,
+      "nll_loss": 0.6325567364692688,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 7.90625,
+      "learning_rate": 5e-06,
+      "log_odds_chosen": 0.015087798237800598,
+      "log_odds_ratio": -0.7565385699272156,
+      "logits/chosen": -2.30287504196167,
+      "logits/rejected": -2.1991920471191406,
+      "logps/chosen": -0.6201391816139221,
+      "logps/rejected": -0.6416058540344238,
+      "loss": 0.6096,
+      "nll_loss": 0.613267719745636,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 7.0,
+      "learning_rate": 4.996562390352354e-06,
+      "log_odds_chosen": 0.13090373575687408,
+      "log_odds_ratio": -0.7056041955947876,
+      "logits/chosen": -2.3028149604797363,
+      "logits/rejected": -2.220900058746338,
+      "logps/chosen": -0.6311284899711609,
+      "logps/rejected": -0.726052463054657,
+      "loss": 0.6535,
+      "nll_loss": 0.6418599486351013,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 5.75,
+      "learning_rate": 4.986259015137485e-06,
+      "log_odds_chosen": 0.18970146775245667,
+      "log_odds_ratio": -0.6792970895767212,
+      "logits/chosen": -2.2931487560272217,
+      "logits/rejected": -2.1606650352478027,
+      "logps/chosen": -0.6621894836425781,
+      "logps/rejected": -0.7548196911811829,
+      "loss": 0.6535,
+      "nll_loss": 0.6817941069602966,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.75,
+      "learning_rate": 4.96911820954103e-06,
+      "log_odds_chosen": 0.10594276338815689,
+      "log_odds_ratio": -0.7069065570831299,
+      "logits/chosen": -2.1914877891540527,
+      "logits/rejected": -2.101252794265747,
+      "logps/chosen": -0.6385573148727417,
+      "logps/rejected": -0.694845974445343,
+      "loss": 0.6445,
+      "nll_loss": 0.6093564033508301,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 7.03125,
+      "learning_rate": 4.945187112281936e-06,
+      "log_odds_chosen": 0.03052571788430214,
+      "log_odds_ratio": -0.7518700361251831,
+      "logits/chosen": -2.319819927215576,
+      "logits/rejected": -2.2670364379882812,
+      "logps/chosen": -0.656802237033844,
+      "logps/rejected": -0.6807278394699097,
+      "loss": 0.6661,
+      "nll_loss": 0.6735944747924805,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.53125,
+      "learning_rate": 4.9145315359768575e-06,
+      "log_odds_chosen": 0.09797719866037369,
+      "log_odds_ratio": -0.7208576798439026,
+      "logits/chosen": -2.3044209480285645,
+      "logits/rejected": -2.2165465354919434,
+      "logps/chosen": -0.612718939781189,
+      "logps/rejected": -0.6638216376304626,
+      "loss": 0.6463,
+      "nll_loss": 0.6212142705917358,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 7.28125,
+      "learning_rate": 4.877235786149681e-06,
+      "log_odds_chosen": -0.003668625606223941,
+      "log_odds_ratio": -0.7583411931991577,
+      "logits/chosen": -2.2496469020843506,
+      "logits/rejected": -2.2018706798553467,
+      "logps/chosen": -0.5735569000244141,
+      "logps/rejected": -0.5976427793502808,
+      "loss": 0.6229,
+      "nll_loss": 0.5609295964241028,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 7.15625,
+      "learning_rate": 4.833402429383947e-06,
+      "log_odds_chosen": 0.01744142733514309,
+      "log_odds_ratio": -0.7390518188476562,
+      "logits/chosen": -2.344698667526245,
+      "logits/rejected": -2.255495548248291,
+      "logps/chosen": -0.659144401550293,
+      "logps/rejected": -0.6820610761642456,
+      "loss": 0.6303,
+      "nll_loss": 0.6458700299263,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 6.125,
+      "learning_rate": 4.783152011255739e-06,
+      "log_odds_chosen": 0.0607575885951519,
+      "log_odds_ratio": -0.7323936223983765,
+      "logits/chosen": -2.2320337295532227,
+      "logits/rejected": -2.177126407623291,
+      "logps/chosen": -0.6184755563735962,
+      "logps/rejected": -0.6612327694892883,
+      "loss": 0.6472,
+      "nll_loss": 0.6245880126953125,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 6.65625,
+      "learning_rate": 4.726622724822781e-06,
+      "log_odds_chosen": 0.07648645341396332,
+      "log_odds_ratio": -0.709121584892273,
+      "logits/chosen": -2.2593894004821777,
+      "logits/rejected": -2.202803134918213,
+      "logps/chosen": -0.6581476330757141,
+      "logps/rejected": -0.7056922912597656,
+      "loss": 0.6518,
+      "nll_loss": 0.6567482352256775,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.84375,
+      "learning_rate": 4.663970030581408e-06,
+      "log_odds_chosen": 0.1157410591840744,
+      "log_odds_ratio": -0.7236483097076416,
+      "logits/chosen": -2.193201780319214,
+      "logits/rejected": -2.150437831878662,
+      "logps/chosen": -0.5841165781021118,
+      "logps/rejected": -0.6441755890846252,
+      "loss": 0.6273,
+      "nll_loss": 0.5958451628684998,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.59375,
+      "learning_rate": 4.59536622893656e-06,
+      "log_odds_chosen": -0.02586597204208374,
+      "log_odds_ratio": -0.7771649360656738,
+      "logits/chosen": -2.2009682655334473,
+      "logits/rejected": -2.112724542617798,
+      "logps/chosen": -0.6882591247558594,
+      "logps/rejected": -0.6998633146286011,
+      "loss": 0.6506,
+      "nll_loss": 0.6941450834274292,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 6.6875,
+      "learning_rate": 4.520999986360555e-06,
+      "log_odds_chosen": 0.06855098158121109,
+      "log_odds_ratio": -0.7186604738235474,
+      "logits/chosen": -2.171708583831787,
+      "logits/rejected": -2.1308529376983643,
+      "logps/chosen": -0.6504184603691101,
+      "logps/rejected": -0.684329628944397,
+      "loss": 0.6221,
+      "nll_loss": 0.6537456512451172,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 8.0625,
+      "learning_rate": 4.441075816543745e-06,
+      "log_odds_chosen": 0.022804971784353256,
+      "log_odds_ratio": -0.741841733455658,
+      "logits/chosen": -2.239063262939453,
+      "logits/rejected": -2.1194045543670654,
+      "logps/chosen": -0.6218129992485046,
+      "logps/rejected": -0.6426461935043335,
+      "loss": 0.6318,
+      "nll_loss": 0.6370661854743958,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 7.0,
+      "learning_rate": 4.355813517963924e-06,
+      "log_odds_chosen": 0.44283628463745117,
+      "log_odds_ratio": -0.5788813829421997,
+      "logits/chosen": -2.2207190990448,
+      "logits/rejected": -2.141242265701294,
+      "logps/chosen": -0.47952336072921753,
+      "logps/rejected": -0.6606315970420837,
+      "loss": 0.524,
+      "nll_loss": 0.4753130078315735,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 7.375,
+      "learning_rate": 4.265447569421234e-06,
+      "log_odds_chosen": 0.46678227186203003,
+      "log_odds_ratio": -0.5757448077201843,
+      "logits/chosen": -2.2942795753479004,
+      "logits/rejected": -2.1979148387908936,
+      "logps/chosen": -0.48276787996292114,
+      "logps/rejected": -0.6674878597259521,
+      "loss": 0.4488,
+      "nll_loss": 0.49083882570266724,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 7.21875,
+      "learning_rate": 4.170226485200899e-06,
+      "log_odds_chosen": 0.5519483685493469,
+      "log_odds_ratio": -0.5382982492446899,
+      "logits/chosen": -2.2755680084228516,
+      "logits/rejected": -2.1837079524993896,
+      "logps/chosen": -0.45342904329299927,
+      "logps/rejected": -0.6915146708488464,
+      "loss": 0.4786,
+      "nll_loss": 0.4660493731498718,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 7.34375,
+      "learning_rate": 4.070412131637139e-06,
+      "log_odds_chosen": 0.4370903968811035,
+      "log_odds_ratio": -0.6020382046699524,
+      "logits/chosen": -2.23408842086792,
+      "logits/rejected": -2.1390938758850098,
+      "logps/chosen": -0.4502868056297302,
+      "logps/rejected": -0.621059238910675,
+      "loss": 0.4861,
+      "nll_loss": 0.4494762420654297,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 8.0,
+      "learning_rate": 3.966279006957781e-06,
+      "log_odds_chosen": 0.5599658489227295,
+      "log_odds_ratio": -0.538549542427063,
+      "logits/chosen": -2.212937831878662,
+      "logits/rejected": -2.1164355278015137,
+      "logps/chosen": -0.466763973236084,
+      "logps/rejected": -0.7057895064353943,
+      "loss": 0.4703,
+      "nll_loss": 0.48790493607521057,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 7.375,
+      "learning_rate": 3.858113486390056e-06,
+      "log_odds_chosen": 0.5336993932723999,
+      "log_odds_ratio": -0.5696849822998047,
+      "logits/chosen": -2.247847318649292,
+      "logits/rejected": -2.1648640632629395,
+      "logps/chosen": -0.4514709413051605,
+      "logps/rejected": -0.7045167684555054,
+      "loss": 0.5033,
+      "nll_loss": 0.4769435524940491,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 10.3125,
+      "learning_rate": 3.7462130346036e-06,
+      "log_odds_chosen": 0.5668686032295227,
+      "log_odds_ratio": -0.5324344635009766,
+      "logits/chosen": -2.2085554599761963,
+      "logits/rejected": -2.1306445598602295,
+      "logps/chosen": -0.4667239189147949,
+      "logps/rejected": -0.701043963432312,
+      "loss": 0.4759,
+      "nll_loss": 0.4993102550506592,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 6.96875,
+      "learning_rate": 3.6308853876565232e-06,
+      "log_odds_chosen": 0.5387176275253296,
+      "log_odds_ratio": -0.5357738137245178,
+      "logits/chosen": -2.256187677383423,
+      "logits/rejected": -2.137636423110962,
+      "logps/chosen": -0.4479009211063385,
+      "logps/rejected": -0.6637527346611023,
+      "loss": 0.4945,
+      "nll_loss": 0.45828866958618164,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 6.375,
+      "learning_rate": 3.512447706694254e-06,
+      "log_odds_chosen": 0.4713989198207855,
+      "log_odds_ratio": -0.5788164138793945,
+      "logits/chosen": -2.2068490982055664,
+      "logits/rejected": -2.1465065479278564,
+      "logps/chosen": -0.46771669387817383,
+      "logps/rejected": -0.670925498008728,
+      "loss": 0.4675,
+      "nll_loss": 0.4617518484592438,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.3912257057285684e-06,
+      "log_odds_chosen": 0.6038286089897156,
+      "log_odds_ratio": -0.53058922290802,
+      "logits/chosen": -2.2398104667663574,
+      "logits/rejected": -2.1177425384521484,
+      "logps/chosen": -0.42343878746032715,
+      "logps/rejected": -0.6755813360214233,
+      "loss": 0.4659,
+      "nll_loss": 0.4260299801826477,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 7.3125,
+      "learning_rate": 3.2675527558954897e-06,
+      "log_odds_chosen": 0.5158039331436157,
+      "log_odds_ratio": -0.5490551590919495,
+      "logits/chosen": -2.240586757659912,
+      "logits/rejected": -2.1683266162872314,
+      "logps/chosen": -0.47749781608581543,
+      "logps/rejected": -0.6999717950820923,
+      "loss": 0.4843,
+      "nll_loss": 0.4936765134334564,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 7.96875,
+      "learning_rate": 3.1417689686554144e-06,
+      "log_odds_chosen": 0.5974913239479065,
+      "log_odds_ratio": -0.5386354327201843,
+      "logits/chosen": -2.2457404136657715,
+      "logits/rejected": -2.2017741203308105,
+      "logps/chosen": -0.4567716717720032,
+      "logps/rejected": -0.7109787464141846,
+      "loss": 0.4855,
+      "nll_loss": 0.46884220838546753,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 6.34375,
+      "learning_rate": 3.0142202604567724e-06,
+      "log_odds_chosen": 0.5235527753829956,
+      "log_odds_ratio": -0.5673588514328003,
+      "logits/chosen": -2.3072521686553955,
+      "logits/rejected": -2.2010462284088135,
+      "logps/chosen": -0.45431017875671387,
+      "logps/rejected": -0.669671893119812,
+      "loss": 0.4738,
+      "nll_loss": 0.4782930314540863,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 6.84375,
+      "learning_rate": 2.8852574014354394e-06,
+      "log_odds_chosen": 0.5463188886642456,
+      "log_odds_ratio": -0.5436448454856873,
+      "logits/chosen": -2.230321168899536,
+      "logits/rejected": -2.136723279953003,
+      "logps/chosen": -0.4296957552433014,
+      "logps/rejected": -0.6486948132514954,
+      "loss": 0.469,
+      "nll_loss": 0.4498000741004944,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 7.03125,
+      "learning_rate": 2.7552350507661063e-06,
+      "log_odds_chosen": 0.3968818187713623,
+      "log_odds_ratio": -0.5953518152236938,
+      "logits/chosen": -2.2960264682769775,
+      "logits/rejected": -2.1944198608398438,
+      "logps/chosen": -0.48995494842529297,
+      "logps/rejected": -0.639137327671051,
+      "loss": 0.4771,
+      "nll_loss": 0.49491143226623535,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 380
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 6.90625,
+      "learning_rate": 2.6245107813184286e-06,
+      "log_odds_chosen": 0.494235098361969,
+      "log_odds_ratio": -0.5915595889091492,
+      "logits/chosen": -2.2012336254119873,
+      "logits/rejected": -2.144287586212158,
+      "logps/chosen": -0.47316503524780273,
+      "logps/rejected": -0.7013116478919983,
+      "loss": 0.4697,
+      "nll_loss": 0.5003570318222046,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 390
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 6.65625,
+      "learning_rate": 2.493444096300273e-06,
+      "log_odds_chosen": 0.4220251142978668,
+      "log_odds_ratio": -0.598805844783783,
+      "logits/chosen": -2.243101119995117,
+      "logits/rejected": -2.149256706237793,
+      "logps/chosen": -0.47102293372154236,
+      "logps/rejected": -0.6398745775222778,
+      "loss": 0.5081,
+      "nll_loss": 0.476499080657959,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 6.75,
+      "learning_rate": 2.3623954405923636e-06,
+      "log_odds_chosen": 0.4254421293735504,
+      "log_odds_ratio": -0.5817403793334961,
+      "logits/chosen": -2.227276086807251,
+      "logits/rejected": -2.1629862785339355,
+      "logps/chosen": -0.44677025079727173,
+      "logps/rejected": -0.6224783658981323,
+      "loss": 0.479,
+      "nll_loss": 0.4805859923362732,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 6.375,
+      "learning_rate": 2.2317252094932383e-06,
+      "log_odds_chosen": 0.5560603737831116,
+      "log_odds_ratio": -0.5513437390327454,
+      "logits/chosen": -2.267571449279785,
+      "logits/rejected": -2.182979106903076,
+      "logps/chosen": -0.4530865252017975,
+      "logps/rejected": -0.6832284331321716,
+      "loss": 0.4704,
+      "nll_loss": 0.4891841411590576,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 420
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 7.28125,
+      "learning_rate": 2.1017927576005657e-06,
+      "log_odds_chosen": 0.5321310758590698,
+      "log_odds_ratio": -0.5503188371658325,
+      "logits/chosen": -2.2212295532226562,
+      "logits/rejected": -2.1423323154449463,
+      "logps/chosen": -0.44568586349487305,
+      "logps/rejected": -0.6636167764663696,
+      "loss": 0.4514,
+      "nll_loss": 0.4601981043815613,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 6.65625,
+      "learning_rate": 1.9729554105544816e-06,
+      "log_odds_chosen": 0.4405423104763031,
+      "log_odds_ratio": -0.5903416872024536,
+      "logits/chosen": -2.1597094535827637,
+      "logits/rejected": -2.088732957839966,
+      "logps/chosen": -0.48640793561935425,
+      "logps/rejected": -0.6836115121841431,
+      "loss": 0.5071,
+      "nll_loss": 0.5123512148857117,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 440
+    },
+    {
+      "epoch": 1.93,
+      "grad_norm": 6.59375,
+      "learning_rate": 1.8455674823607312e-06,
+      "log_odds_chosen": 0.3645675778388977,
+      "log_odds_ratio": -0.6205390095710754,
+      "logits/chosen": -2.248469829559326,
+      "logits/rejected": -2.1717073917388916,
+      "logps/chosen": -0.48888254165649414,
+      "logps/rejected": -0.6395884156227112,
+      "loss": 0.4756,
+      "nll_loss": 0.5086942911148071,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 6.78125,
+      "learning_rate": 1.7199793009960766e-06,
+      "log_odds_chosen": 0.5230408310890198,
+      "log_odds_ratio": -0.5633384585380554,
+      "logits/chosen": -2.1712698936462402,
+      "logits/rejected": -2.1275506019592285,
+      "logps/chosen": -0.49090108275413513,
+      "logps/rejected": -0.7094160914421082,
+      "loss": 0.4833,
+      "nll_loss": 0.5040683150291443,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 7.625,
+      "learning_rate": 1.5965362449756317e-06,
+      "log_odds_chosen": 0.6898726224899292,
+      "log_odds_ratio": -0.4951675534248352,
+      "logits/chosen": -2.271798610687256,
+      "logits/rejected": -2.167448043823242,
+      "logps/chosen": -0.4061620831489563,
+      "logps/rejected": -0.6713688969612122,
+      "loss": 0.4494,
+      "nll_loss": 0.4319891333580017,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 470
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 8.0,
+      "learning_rate": 1.4755777935316412e-06,
+      "log_odds_chosen": 0.9442523121833801,
+      "log_odds_ratio": -0.4286450445652008,
+      "logits/chosen": -2.326359272003174,
+      "logits/rejected": -2.1804490089416504,
+      "logps/chosen": -0.3767296373844147,
+      "logps/rejected": -0.7195509672164917,
+      "loss": 0.3793,
+      "nll_loss": 0.3976900279521942,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 480
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 6.3125,
+      "learning_rate": 1.3574365930158272e-06,
+      "log_odds_chosen": 0.9110834002494812,
+      "log_odds_ratio": -0.4287477433681488,
+      "logits/chosen": -2.2323246002197266,
+      "logits/rejected": -2.1740031242370605,
+      "logps/chosen": -0.34097957611083984,
+      "logps/rejected": -0.6637391448020935,
+      "loss": 0.3725,
+      "nll_loss": 0.3685534596443176,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 490
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 6.5,
+      "learning_rate": 1.242437542092731e-06,
+      "log_odds_chosen": 1.0058963298797607,
+      "log_odds_ratio": -0.3893057703971863,
+      "logits/chosen": -2.2164254188537598,
+      "logits/rejected": -2.159911870956421,
+      "logps/chosen": -0.3380836546421051,
+      "logps/rejected": -0.6879861950874329,
+      "loss": 0.3836,
+      "nll_loss": 0.3611399233341217,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 6.6875,
+      "learning_rate": 1.1308968982398893e-06,
+      "log_odds_chosen": 1.015363097190857,
+      "log_odds_ratio": -0.3953540325164795,
+      "logits/chosen": -2.239375591278076,
+      "logits/rejected": -2.1401748657226562,
+      "logps/chosen": -0.32685962319374084,
+      "logps/rejected": -0.714621901512146,
+      "loss": 0.3588,
+      "nll_loss": 0.3464065492153168,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 7.375,
+      "learning_rate": 1.0231214080120354e-06,
+      "log_odds_chosen": 0.9830226898193359,
+      "log_odds_ratio": -0.42418375611305237,
+      "logits/chosen": -2.203508138656616,
+      "logits/rejected": -2.155480146408081,
+      "logps/chosen": -0.3562384247779846,
+      "logps/rejected": -0.7052286267280579,
+      "loss": 0.3706,
+      "nll_loss": 0.37242117524147034,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 6.125,
+      "learning_rate": 9.194074634611577e-07,
+      "log_odds_chosen": 0.9658070802688599,
+      "log_odds_ratio": -0.40443453192710876,
+      "logits/chosen": -2.27958607673645,
+      "logits/rejected": -2.1977391242980957,
+      "logps/chosen": -0.34767287969589233,
+      "logps/rejected": -0.6850040555000305,
+      "loss": 0.3652,
+      "nll_loss": 0.3679281175136566,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 530
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 6.5,
+      "learning_rate": 8.200402870323634e-07,
+      "log_odds_chosen": 1.0082114934921265,
+      "log_odds_ratio": -0.4111156463623047,
+      "logits/chosen": -2.2096288204193115,
+      "logits/rejected": -2.115715503692627,
+      "logps/chosen": -0.36051854491233826,
+      "logps/rejected": -0.724047064781189,
+      "loss": 0.3715,
+      "nll_loss": 0.3693843483924866,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 540
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 6.59375,
+      "learning_rate": 7.252931471771322e-07,
+      "log_odds_chosen": 1.1489967107772827,
+      "log_odds_ratio": -0.36786437034606934,
+      "logits/chosen": -2.3240292072296143,
+      "logits/rejected": -2.2296738624572754,
+      "logps/chosen": -0.32746613025665283,
+      "logps/rejected": -0.7155576944351196,
+      "loss": 0.3592,
+      "nll_loss": 0.33152374625205994,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 550
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 7.71875,
+      "learning_rate": 6.354266068411078e-07,
+      "log_odds_chosen": 0.9698125720024109,
+      "log_odds_ratio": -0.4362240731716156,
+      "logits/chosen": -2.169530153274536,
+      "logits/rejected": -2.1334238052368164,
+      "logps/chosen": -0.3798636496067047,
+      "logps/rejected": -0.7286175489425659,
+      "loss": 0.3918,
+      "nll_loss": 0.40456095337867737,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 560
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 7.09375,
+      "learning_rate": 5.50687806893139e-07,
+      "log_odds_chosen": 1.0643595457077026,
+      "log_odds_ratio": -0.39470165967941284,
+      "logits/chosen": -2.20218825340271,
+      "logits/rejected": -2.2017059326171875,
+      "logps/chosen": -0.3234565854072571,
+      "logps/rejected": -0.6679071187973022,
+      "loss": 0.3741,
+      "nll_loss": 0.3704506456851959,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 570
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 7.6875,
+      "learning_rate": 4.7130978646620807e-07,
+      "log_odds_chosen": 1.1568490266799927,
+      "log_odds_ratio": -0.3843044340610504,
+      "logits/chosen": -2.246670961380005,
+      "logits/rejected": -2.117475748062134,
+      "logps/chosen": -0.3415004014968872,
+      "logps/rejected": -0.7403726577758789,
+      "loss": 0.3564,
+      "nll_loss": 0.39345091581344604,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 580
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 6.125,
+      "learning_rate": 3.975108420793819e-07,
+      "log_odds_chosen": 1.017449140548706,
+      "log_odds_ratio": -0.4111986756324768,
+      "logits/chosen": -2.182363271713257,
+      "logits/rejected": -2.1441586017608643,
+      "logps/chosen": -0.3217340111732483,
+      "logps/rejected": -0.6855174899101257,
+      "loss": 0.361,
+      "nll_loss": 0.34829622507095337,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 590
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 7.28125,
+      "learning_rate": 3.294939273032272e-07,
+      "log_odds_chosen": 1.0704463720321655,
+      "log_odds_ratio": -0.376108318567276,
+      "logits/chosen": -2.1767077445983887,
+      "logits/rejected": -2.1506667137145996,
+      "logps/chosen": -0.32282644510269165,
+      "logps/rejected": -0.7082036733627319,
+      "loss": 0.34,
+      "nll_loss": 0.32364171743392944,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 6.5,
+      "learning_rate": 2.6744609461969523e-07,
+      "log_odds_chosen": 1.051203966140747,
+      "log_odds_ratio": -0.39061832427978516,
+      "logits/chosen": -2.290379047393799,
+      "logits/rejected": -2.220198154449463,
+      "logps/chosen": -0.32938411831855774,
+      "logps/rejected": -0.7165583968162537,
+      "loss": 0.3702,
+      "nll_loss": 0.338884174823761,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 610
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 6.84375,
+      "learning_rate": 2.1153798101138405e-07,
+      "log_odds_chosen": 1.1411008834838867,
+      "log_odds_ratio": -0.360759973526001,
+      "logits/chosen": -2.221855878829956,
+      "logits/rejected": -2.1710667610168457,
+      "logps/chosen": -0.3297441303730011,
+      "logps/rejected": -0.7233366370201111,
+      "loss": 0.3585,
+      "nll_loss": 0.35538965463638306,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 620
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 7.5625,
+      "learning_rate": 1.61923338694871e-07,
+      "log_odds_chosen": 1.0430134534835815,
+      "log_odds_ratio": -0.4124155044555664,
+      "logits/chosen": -2.2372210025787354,
+      "logits/rejected": -2.169727087020874,
+      "logps/chosen": -0.343710720539093,
+      "logps/rejected": -0.740007758140564,
+      "loss": 0.3551,
+      "nll_loss": 0.35884636640548706,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 630
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.375,
+      "learning_rate": 1.1873861228862998e-07,
+      "log_odds_chosen": 1.1086117029190063,
+      "log_odds_ratio": -0.3817860186100006,
+      "logits/chosen": -2.2177319526672363,
+      "logits/rejected": -2.130946397781372,
+      "logps/chosen": -0.3493684232234955,
+      "logps/rejected": -0.7561189532279968,
+      "loss": 0.3626,
+      "nll_loss": 0.37719854712486267,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 640
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 7.0,
+      "learning_rate": 8.210256357836065e-08,
+      "log_odds_chosen": 1.211117148399353,
+      "log_odds_ratio": -0.34444934129714966,
+      "logits/chosen": -2.181938886642456,
+      "logits/rejected": -2.1168627738952637,
+      "logps/chosen": -0.30442455410957336,
+      "logps/rejected": -0.723738968372345,
+      "loss": 0.3425,
+      "nll_loss": 0.31909602880477905,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 650
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 7.25,
+      "learning_rate": 5.21159449116615e-08,
+      "log_odds_chosen": 0.889040470123291,
+      "log_odds_ratio": -0.46176376938819885,
+      "logits/chosen": -2.210618495941162,
+      "logits/rejected": -2.131258726119995,
+      "logps/chosen": -0.37134605646133423,
+      "logps/rejected": -0.6827694773674011,
+      "loss": 0.3686,
+      "nll_loss": 0.37423044443130493,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 660
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 6.53125,
+      "learning_rate": 2.8861222120235845e-08,
+      "log_odds_chosen": 1.068619966506958,
+      "log_odds_ratio": -0.3856962025165558,
+      "logits/chosen": -2.163769245147705,
+      "logits/rejected": -2.134917736053467,
+      "logps/chosen": -0.30325040221214294,
+      "logps/rejected": -0.6523526906967163,
+      "loss": 0.3648,
+      "nll_loss": 0.336664617061615,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 670
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 7.46875,
+      "learning_rate": 1.2402347731620412e-08,
+      "log_odds_chosen": 0.9644078016281128,
+      "log_odds_ratio": -0.40152567625045776,
+      "logits/chosen": -2.2033181190490723,
+      "logits/rejected": -2.091287136077881,
+      "logps/chosen": -0.36845338344573975,
+      "logps/rejected": -0.7090677618980408,
+      "loss": 0.3648,
+      "nll_loss": 0.38515713810920715,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 680
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 7.15625,
+      "learning_rate": 2.7845850941254914e-09,
+      "log_odds_chosen": 1.0706063508987427,
+      "log_odds_ratio": -0.3853154182434082,
+      "logits/chosen": -2.2872862815856934,
+      "logits/rejected": -2.2065258026123047,
+      "logps/chosen": -0.32825738191604614,
+      "logps/rejected": -0.6639867424964905,
+      "loss": 0.3568,
+      "nll_loss": 0.35901403427124023,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 690
+    },
+    {
+      "epoch": 3.0,
+      "step": 699,
+      "total_flos": 0.0,
+      "train_loss": 0.500827480283418,
+      "train_runtime": 21486.5219,
+      "train_samples_per_second": 2.084,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 699,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}