Model save

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-dpo-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. -->
+
+# zephyr-7b-dpo-full
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5000
+- Rewards/chosen: -2.3681
+- Rewards/rejected: -3.4811
+- Rewards/accuracies: 0.7695
+- Rewards/margins: 1.1129
+- Logps/rejected: -610.7911
+- Logps/chosen: -499.4172
+- Logits/rejected: -0.0390
+- Logits/chosen: -0.5081
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- 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
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5875        | 0.21  | 100  | 0.5814          | -0.6485        | -1.1103          | 0.6953             | 0.4618          | -373.7126      | -327.4548    | -1.8929         | -1.8392       |
+| 0.5306        | 0.42  | 200  | 0.5258          | -1.1476        | -1.9595          | 0.7578             | 0.8118          | -458.6297      | -377.3649    | -0.1647         | -0.4835       |
+| 0.5097        | 0.63  | 300  | 0.5079          | -2.3601        | -3.3817          | 0.7656             | 1.0216          | -600.8517      | -498.6086    | -0.0574         | -0.4658       |
+| 0.4906        | 0.84  | 400  | 0.5000          | -2.3681        | -3.4811          | 0.7695             | 1.1129          | -610.7911      | -499.4172    | -0.0390         | -0.5081       |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.535196884905444,
+    "train_runtime": 3527.4214,
+    "train_samples": 61135,
+    "train_samples_per_second": 17.331,
+    "train_steps_per_second": 0.136
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23fa8169c3c25ed7df40b8ed99b8e24e67385bcbb0312e5ed0f5ff2b7ac9321
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91acbf3d987a1c6de2dfbabfe72245eaf0557444a725eb8366b94e26dc2ef45e
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e11803ee3075f50990ecd10b6daba209733ec926ee98208fdbe447c8850772
+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"
+  }
+}

runs/Mar11_14-59-16_node-0/events.out.tfevents.1710194390.node-0.16413.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed7ccdb04fd8b4308ab8be4fd47242e782f14027c670a20da81b20630ab9c96
-size 35714
+oid sha256:a6a58b6d7a03de6e774bf4ec060d4adcbb7c4f152706308844414284bae1de74
+size 40884

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.535196884905444,
+    "train_runtime": 3527.4214,
+    "train_samples": 61135,
+    "train_samples_per_second": 17.331,
+    "train_steps_per_second": 0.136
+}

trainer_state.json

@@ -0,0 +1,814 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 478,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 8.482095207381906,
+      "learning_rate": 1.0416666666666666e-08,
+      "logits/chosen": -2.715719223022461,
+      "logits/rejected": -2.648977279663086,
+      "logps/chosen": -280.43304443359375,
+      "logps/rejected": -269.5838623046875,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 8.16883844563723,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -2.732839345932007,
+      "logits/rejected": -2.667829990386963,
+      "logps/chosen": -252.18836975097656,
+      "logps/rejected": -247.36721801757812,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.4027777910232544,
+      "rewards/chosen": -0.00020123104332014918,
+      "rewards/margins": -0.000496760243549943,
+      "rewards/rejected": 0.00029552922933362424,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 14.177063698718772,
+      "learning_rate": 2.0833333333333333e-07,
+      "logits/chosen": -2.69161057472229,
+      "logits/rejected": -2.6473488807678223,
+      "logps/chosen": -281.9129333496094,
+      "logps/rejected": -240.79598999023438,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.0002729900588747114,
+      "rewards/margins": 0.0022440399043262005,
+      "rewards/rejected": -0.002517030341550708,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.049842796547402,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -2.7057762145996094,
+      "logits/rejected": -2.6666598320007324,
+      "logps/chosen": -263.8976135253906,
+      "logps/rejected": -272.29376220703125,
+      "loss": 0.688,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 0.005987819284200668,
+      "rewards/margins": 0.008191236294806004,
+      "rewards/rejected": -0.0022034167777746916,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.064536836305289,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -2.644676446914673,
+      "logits/rejected": -2.6523287296295166,
+      "logps/chosen": -250.64651489257812,
+      "logps/rejected": -240.74032592773438,
+      "loss": 0.6775,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.03351370617747307,
+      "rewards/margins": 0.024272698909044266,
+      "rewards/rejected": 0.009241009131073952,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 10.48307069571783,
+      "learning_rate": 4.999733114418725e-07,
+      "logits/chosen": -2.61690616607666,
+      "logits/rejected": -2.606698989868164,
+      "logps/chosen": -280.32537841796875,
+      "logps/rejected": -285.14044189453125,
+      "loss": 0.6572,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 0.027328694239258766,
+      "rewards/margins": 0.08270208537578583,
+      "rewards/rejected": -0.05537338927388191,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 11.217495552902317,
+      "learning_rate": 4.990398100856366e-07,
+      "logits/chosen": -2.6028363704681396,
+      "logits/rejected": -2.567634344100952,
+      "logps/chosen": -257.1751403808594,
+      "logps/rejected": -286.7103271484375,
+      "loss": 0.6382,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.04173869267106056,
+      "rewards/margins": 0.14793893694877625,
+      "rewards/rejected": -0.1896776258945465,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 17.002512653941917,
+      "learning_rate": 4.967775735898179e-07,
+      "logits/chosen": -2.5477585792541504,
+      "logits/rejected": -2.5538854598999023,
+      "logps/chosen": -292.3646240234375,
+      "logps/rejected": -295.1927795410156,
+      "loss": 0.6089,
+      "rewards/accuracies": 0.6312500238418579,
+      "rewards/chosen": -0.17977146804332733,
+      "rewards/margins": 0.22043642401695251,
+      "rewards/rejected": -0.40020790696144104,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 20.83722381714638,
+      "learning_rate": 4.931986719649298e-07,
+      "logits/chosen": -2.428433895111084,
+      "logits/rejected": -2.4765429496765137,
+      "logps/chosen": -269.8500671386719,
+      "logps/rejected": -280.10003662109375,
+      "loss": 0.6115,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.11873555183410645,
+      "rewards/margins": 0.21846923232078552,
+      "rewards/rejected": -0.3372047543525696,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 20.582635256945927,
+      "learning_rate": 4.883222001996351e-07,
+      "logits/chosen": -2.3149566650390625,
+      "logits/rejected": -2.3007912635803223,
+      "logps/chosen": -331.8517761230469,
+      "logps/rejected": -353.4700012207031,
+      "loss": 0.6084,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.4723566174507141,
+      "rewards/margins": 0.2896661162376404,
+      "rewards/rejected": -0.7620226740837097,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 15.474211826471516,
+      "learning_rate": 4.821741763807186e-07,
+      "logits/chosen": -2.2471911907196045,
+      "logits/rejected": -2.2106168270111084,
+      "logps/chosen": -346.5975646972656,
+      "logps/rejected": -342.70501708984375,
+      "loss": 0.5875,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.5387172698974609,
+      "rewards/margins": 0.4208316206932068,
+      "rewards/rejected": -0.9595489501953125,
+      "step": 100
+    },
+    {
+      "epoch": 0.21,
+      "eval_logits/chosen": -1.839242935180664,
+      "eval_logits/rejected": -1.8929309844970703,
+      "eval_logps/chosen": -327.45477294921875,
+      "eval_logps/rejected": -373.7126159667969,
+      "eval_loss": 0.5814013481140137,
+      "eval_rewards/accuracies": 0.6953125,
+      "eval_rewards/chosen": -0.6485257148742676,
+      "eval_rewards/margins": 0.46177732944488525,
+      "eval_rewards/rejected": -1.1103030443191528,
+      "eval_runtime": 42.9635,
+      "eval_samples_per_second": 46.551,
+      "eval_steps_per_second": 0.745,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 20.231938142939548,
+      "learning_rate": 4.747874028753375e-07,
+      "logits/chosen": -1.7017923593521118,
+      "logits/rejected": -1.6744320392608643,
+      "logps/chosen": -330.83038330078125,
+      "logps/rejected": -384.0965576171875,
+      "loss": 0.559,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -0.6345968246459961,
+      "rewards/margins": 0.5422910451889038,
+      "rewards/rejected": -1.1768878698349,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 33.96451578064435,
+      "learning_rate": 4.662012913161997e-07,
+      "logits/chosen": -1.5577061176300049,
+      "logits/rejected": -1.454756498336792,
+      "logps/chosen": -354.79632568359375,
+      "logps/rejected": -374.60076904296875,
+      "loss": 0.5508,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6455836892127991,
+      "rewards/margins": 0.6170965433120728,
+      "rewards/rejected": -1.2626802921295166,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 22.138057395490627,
+      "learning_rate": 4.5646165232345103e-07,
+      "logits/chosen": -1.985395073890686,
+      "logits/rejected": -1.7330490350723267,
+      "logps/chosen": -381.68524169921875,
+      "logps/rejected": -393.6003723144531,
+      "loss": 0.5691,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.6896110773086548,
+      "rewards/margins": 0.46295279264450073,
+      "rewards/rejected": -1.1525638103485107,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 22.948235111766778,
+      "learning_rate": 4.456204510851956e-07,
+      "logits/chosen": -1.7121162414550781,
+      "logits/rejected": -1.4992659091949463,
+      "logps/chosen": -352.444580078125,
+      "logps/rejected": -359.44293212890625,
+      "loss": 0.5444,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.7159131765365601,
+      "rewards/margins": 0.5610858798027039,
+      "rewards/rejected": -1.2769991159439087,
+      "step": 140
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 21.94614729668817,
+      "learning_rate": 4.337355301007335e-07,
+      "logits/chosen": -1.6999915838241577,
+      "logits/rejected": -1.5280932188034058,
+      "logps/chosen": -363.3777770996094,
+      "logps/rejected": -409.53472900390625,
+      "loss": 0.5354,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.6176407933235168,
+      "rewards/margins": 0.7246734499931335,
+      "rewards/rejected": -1.3423142433166504,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 25.951614311748312,
+      "learning_rate": 4.2087030056579986e-07,
+      "logits/chosen": -0.8817731142044067,
+      "logits/rejected": -0.6137579679489136,
+      "logps/chosen": -382.1938171386719,
+      "logps/rejected": -432.11004638671875,
+      "loss": 0.5293,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.0363513231277466,
+      "rewards/margins": 0.7439759373664856,
+      "rewards/rejected": -1.7803272008895874,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 22.62183660087882,
+      "learning_rate": 4.070934040463998e-07,
+      "logits/chosen": -0.8362399339675903,
+      "logits/rejected": -0.5129006505012512,
+      "logps/chosen": -383.85943603515625,
+      "logps/rejected": -450.67376708984375,
+      "loss": 0.5396,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.1981004476547241,
+      "rewards/margins": 0.5252794623374939,
+      "rewards/rejected": -1.7233800888061523,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 20.471718314655647,
+      "learning_rate": 3.9247834624635404e-07,
+      "logits/chosen": -1.1186776161193848,
+      "logits/rejected": -0.807415783405304,
+      "logps/chosen": -367.24517822265625,
+      "logps/rejected": -383.65325927734375,
+      "loss": 0.5423,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.7441693544387817,
+      "rewards/margins": 0.7058154344558716,
+      "rewards/rejected": -1.4499847888946533,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 27.806972171143425,
+      "learning_rate": 3.7710310482256523e-07,
+      "logits/chosen": -0.8124464750289917,
+      "logits/rejected": -0.3878273069858551,
+      "logps/chosen": -388.7113342285156,
+      "logps/rejected": -429.1011657714844,
+      "loss": 0.5411,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -1.1005661487579346,
+      "rewards/margins": 0.6401538252830505,
+      "rewards/rejected": -1.7407200336456299,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 26.53253409564454,
+      "learning_rate": 3.610497133404795e-07,
+      "logits/chosen": -0.11316045373678207,
+      "logits/rejected": 0.337258517742157,
+      "logps/chosen": -417.2351989746094,
+      "logps/rejected": -437.7659606933594,
+      "loss": 0.5306,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.1853481531143188,
+      "rewards/margins": 0.7383456826210022,
+      "rewards/rejected": -1.9236938953399658,
+      "step": 200
+    },
+    {
+      "epoch": 0.42,
+      "eval_logits/chosen": -0.4834875464439392,
+      "eval_logits/rejected": -0.16467474400997162,
+      "eval_logps/chosen": -377.3648681640625,
+      "eval_logps/rejected": -458.6296691894531,
+      "eval_loss": 0.5258087515830994,
+      "eval_rewards/accuracies": 0.7578125,
+      "eval_rewards/chosen": -1.1476268768310547,
+      "eval_rewards/margins": 0.8118469715118408,
+      "eval_rewards/rejected": -1.959473729133606,
+      "eval_runtime": 42.8446,
+      "eval_samples_per_second": 46.68,
+      "eval_steps_per_second": 0.747,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 32.607007304168285,
+      "learning_rate": 3.4440382358952115e-07,
+      "logits/chosen": -0.4726165235042572,
+      "logits/rejected": 0.2889423966407776,
+      "logps/chosen": -445.2005310058594,
+      "logps/rejected": -516.150390625,
+      "loss": 0.5157,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -1.5719295740127563,
+      "rewards/margins": 0.899932861328125,
+      "rewards/rejected": -2.471862316131592,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 26.982376912169133,
+      "learning_rate": 3.272542485937368e-07,
+      "logits/chosen": 0.02971530519425869,
+      "logits/rejected": 0.6972896456718445,
+      "logps/chosen": -488.6690979003906,
+      "logps/rejected": -517.7215576171875,
+      "loss": 0.5045,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.9397350549697876,
+      "rewards/margins": 0.67905592918396,
+      "rewards/rejected": -2.618790626525879,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 28.31686307704009,
+      "learning_rate": 3.096924887558854e-07,
+      "logits/chosen": 0.3274112641811371,
+      "logits/rejected": 1.6159236431121826,
+      "logps/chosen": -472.36590576171875,
+      "logps/rejected": -560.3911743164062,
+      "loss": 0.5157,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -2.139970302581787,
+      "rewards/margins": 0.9002918004989624,
+      "rewards/rejected": -3.040262460708618,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 26.93455267413187,
+      "learning_rate": 2.9181224366319943e-07,
+      "logits/chosen": 0.34222739934921265,
+      "logits/rejected": 1.275580644607544,
+      "logps/chosen": -493.95916748046875,
+      "logps/rejected": -570.4260864257812,
+      "loss": 0.4844,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -2.126845598220825,
+      "rewards/margins": 0.9677503705024719,
+      "rewards/rejected": -3.0945961475372314,
+      "step": 240
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 34.97761081158377,
+      "learning_rate": 2.7370891215954565e-07,
+      "logits/chosen": 0.15051239728927612,
+      "logits/rejected": 1.3550792932510376,
+      "logps/chosen": -447.21490478515625,
+      "logps/rejected": -547.626708984375,
+      "loss": 0.5157,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -2.229414463043213,
+      "rewards/margins": 1.004492998123169,
+      "rewards/rejected": -3.2339072227478027,
+      "step": 250
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 22.98186057582904,
+      "learning_rate": 2.55479083351317e-07,
+      "logits/chosen": -0.6737252473831177,
+      "logits/rejected": -0.22596630454063416,
+      "logps/chosen": -423.21124267578125,
+      "logps/rejected": -537.1641845703125,
+      "loss": 0.4931,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.5507694482803345,
+      "rewards/margins": 1.1678037643432617,
+      "rewards/rejected": -2.7185730934143066,
+      "step": 260
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 24.568187901601522,
+      "learning_rate": 2.3722002126275822e-07,
+      "logits/chosen": -0.7251144647598267,
+      "logits/rejected": 0.055858515202999115,
+      "logps/chosen": -460.47369384765625,
+      "logps/rejected": -515.4779663085938,
+      "loss": 0.5056,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.7928097248077393,
+      "rewards/margins": 0.9766537547111511,
+      "rewards/rejected": -2.769463300704956,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 26.18745823449182,
+      "learning_rate": 2.19029145890313e-07,
+      "logits/chosen": -0.2248018980026245,
+      "logits/rejected": 0.7499777674674988,
+      "logps/chosen": -570.017822265625,
+      "logps/rejected": -637.1007690429688,
+      "loss": 0.4807,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -2.686659097671509,
+      "rewards/margins": 1.049829125404358,
+      "rewards/rejected": -3.736487865447998,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 27.843254345626296,
+      "learning_rate": 2.0100351342479216e-07,
+      "logits/chosen": 0.017834633588790894,
+      "logits/rejected": 0.5087012052536011,
+      "logps/chosen": -523.2457275390625,
+      "logps/rejected": -614.5767211914062,
+      "loss": 0.4986,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -2.559013605117798,
+      "rewards/margins": 0.9906851053237915,
+      "rewards/rejected": -3.5496985912323,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 28.812343531542734,
+      "learning_rate": 1.8323929841460178e-07,
+      "logits/chosen": -0.09833024442195892,
+      "logits/rejected": 0.13667245209217072,
+      "logps/chosen": -530.9118041992188,
+      "logps/rejected": -594.4251098632812,
+      "loss": 0.5097,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -2.618612766265869,
+      "rewards/margins": 0.6055675745010376,
+      "rewards/rejected": -3.224180221557617,
+      "step": 300
+    },
+    {
+      "epoch": 0.63,
+      "eval_logits/chosen": -0.46580713987350464,
+      "eval_logits/rejected": -0.05736924335360527,
+      "eval_logps/chosen": -498.608642578125,
+      "eval_logps/rejected": -600.8517456054688,
+      "eval_loss": 0.5078553557395935,
+      "eval_rewards/accuracies": 0.765625,
+      "eval_rewards/chosen": -2.3600645065307617,
+      "eval_rewards/margins": 1.021630048751831,
+      "eval_rewards/rejected": -3.3816945552825928,
+      "eval_runtime": 42.9133,
+      "eval_samples_per_second": 46.606,
+      "eval_steps_per_second": 0.746,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 24.395908084810543,
+      "learning_rate": 1.6583128063291573e-07,
+      "logits/chosen": -0.20998772978782654,
+      "logits/rejected": 0.597333550453186,
+      "logps/chosen": -553.8638305664062,
+      "logps/rejected": -622.6854248046875,
+      "loss": 0.4601,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -2.6587719917297363,
+      "rewards/margins": 1.019250512123108,
+      "rewards/rejected": -3.678022861480713,
+      "step": 310
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 34.66768420911215,
+      "learning_rate": 1.488723393865766e-07,
+      "logits/chosen": 0.16718712449073792,
+      "logits/rejected": 0.9329349398612976,
+      "logps/chosen": -593.7220458984375,
+      "logps/rejected": -669.1134033203125,
+      "loss": 0.4733,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -3.0446815490722656,
+      "rewards/margins": 1.103857159614563,
+      "rewards/rejected": -4.1485395431518555,
+      "step": 320
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 28.471803594507218,
+      "learning_rate": 1.3245295796480788e-07,
+      "logits/chosen": -0.11941705644130707,
+      "logits/rejected": 0.6031097173690796,
+      "logps/chosen": -576.390869140625,
+      "logps/rejected": -662.9435424804688,
+      "loss": 0.4956,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -2.895800828933716,
+      "rewards/margins": 1.0525661706924438,
+      "rewards/rejected": -3.9483673572540283,
+      "step": 330
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 29.920730024726208,
+      "learning_rate": 1.1666074087171627e-07,
+      "logits/chosen": -0.6586230397224426,
+      "logits/rejected": -0.01618196628987789,
+      "logps/chosen": -558.61328125,
+      "logps/rejected": -645.0929565429688,
+      "loss": 0.4901,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -2.6631388664245605,
+      "rewards/margins": 0.9750139117240906,
+      "rewards/rejected": -3.638153076171875,
+      "step": 340
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 28.451943555198234,
+      "learning_rate": 1.0157994641835734e-07,
+      "logits/chosen": -0.27327781915664673,
+      "logits/rejected": 0.1500699818134308,
+      "logps/chosen": -551.64501953125,
+      "logps/rejected": -615.7404174804688,
+      "loss": 0.5079,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -2.8532228469848633,
+      "rewards/margins": 0.7952502369880676,
+      "rewards/rejected": -3.6484732627868652,
+      "step": 350
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 25.677922944710783,
+      "learning_rate": 8.729103716819111e-08,
+      "logits/chosen": -0.08269649744033813,
+      "logits/rejected": 0.27684250473976135,
+      "logps/chosen": -541.1990966796875,
+      "logps/rejected": -651.2036743164062,
+      "loss": 0.4674,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -2.9707937240600586,
+      "rewards/margins": 0.9196038246154785,
+      "rewards/rejected": -3.8903980255126953,
+      "step": 360
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 36.170517312989006,
+      "learning_rate": 7.387025063449081e-08,
+      "logits/chosen": -0.2130926102399826,
+      "logits/rejected": 0.6245878338813782,
+      "logps/chosen": -593.176513671875,
+      "logps/rejected": -702.429443359375,
+      "loss": 0.4914,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -3.0834755897521973,
+      "rewards/margins": 1.1826813220977783,
+      "rewards/rejected": -4.266157150268555,
+      "step": 370
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 29.948938424368286,
+      "learning_rate": 6.138919252022435e-08,
+      "logits/chosen": -0.31227773427963257,
+      "logits/rejected": 0.1758570820093155,
+      "logps/chosen": -569.8441162109375,
+      "logps/rejected": -653.1160278320312,
+      "loss": 0.4834,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -2.861605644226074,
+      "rewards/margins": 1.1251481771469116,
+      "rewards/rejected": -3.9867539405822754,
+      "step": 380
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 28.643050867948876,
+      "learning_rate": 4.991445467064689e-08,
+      "logits/chosen": -0.4378163814544678,
+      "logits/rejected": 0.1975017786026001,
+      "logps/chosen": -487.02447509765625,
+      "logps/rejected": -627.4256591796875,
+      "loss": 0.4863,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -2.4755725860595703,
+      "rewards/margins": 1.2951563596725464,
+      "rewards/rejected": -3.770728588104248,
+      "step": 390
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 28.740512536833982,
+      "learning_rate": 3.9507259776993954e-08,
+      "logits/chosen": -0.464282363653183,
+      "logits/rejected": 0.3086758852005005,
+      "logps/chosen": -510.72564697265625,
+      "logps/rejected": -584.2462158203125,
+      "loss": 0.4906,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -2.4956374168395996,
+      "rewards/margins": 0.9018915891647339,
+      "rewards/rejected": -3.397528886795044,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "eval_logits/chosen": -0.5081287026405334,
+      "eval_logits/rejected": -0.03897371515631676,
+      "eval_logps/chosen": -499.4172058105469,
+      "eval_logps/rejected": -610.7911376953125,
+      "eval_loss": 0.49998462200164795,
+      "eval_rewards/accuracies": 0.76953125,
+      "eval_rewards/chosen": -2.368149995803833,
+      "eval_rewards/margins": 1.1129380464553833,
+      "eval_rewards/rejected": -3.4810879230499268,
+      "eval_runtime": 43.5613,
+      "eval_samples_per_second": 45.912,
+      "eval_steps_per_second": 0.735,
+      "step": 400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 29.137185743173024,
+      "learning_rate": 3.022313472693447e-08,
+      "logits/chosen": -0.427814781665802,
+      "logits/rejected": 0.47378939390182495,
+      "logps/chosen": -502.87939453125,
+      "logps/rejected": -579.4691162109375,
+      "loss": 0.5048,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -2.4262542724609375,
+      "rewards/margins": 0.9697957038879395,
+      "rewards/rejected": -3.396049976348877,
+      "step": 410
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 28.72794205317694,
+      "learning_rate": 2.2111614344599684e-08,
+      "logits/chosen": -0.4604805111885071,
+      "logits/rejected": 0.19487139582633972,
+      "logps/chosen": -517.6533813476562,
+      "logps/rejected": -557.2385864257812,
+      "loss": 0.4911,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -2.416501760482788,
+      "rewards/margins": 0.9597095251083374,
+      "rewards/rejected": -3.376211643218994,
+      "step": 420
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 21.80245746988776,
+      "learning_rate": 1.521597710086439e-08,
+      "logits/chosen": -0.3804924488067627,
+      "logits/rejected": 0.39526861906051636,
+      "logps/chosen": -535.6771240234375,
+      "logps/rejected": -618.59326171875,
+      "loss": 0.4719,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -2.5517053604125977,
+      "rewards/margins": 1.1444313526153564,
+      "rewards/rejected": -3.696136474609375,
+      "step": 430
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 25.533460874638475,
+      "learning_rate": 9.57301420397924e-09,
+      "logits/chosen": -0.2722262442111969,
+      "logits/rejected": 0.6270692944526672,
+      "logps/chosen": -534.4539184570312,
+      "logps/rejected": -636.7295532226562,
+      "loss": 0.4921,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -2.657174587249756,
+      "rewards/margins": 1.1696617603302002,
+      "rewards/rejected": -3.826836347579956,
+      "step": 440
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 29.41617255057514,
+      "learning_rate": 5.212833302556258e-09,
+      "logits/chosen": -0.4902656078338623,
+      "logits/rejected": 0.2050538957118988,
+      "logps/chosen": -552.1812744140625,
+      "logps/rejected": -615.8868408203125,
+      "loss": 0.4784,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -2.5670862197875977,
+      "rewards/margins": 1.0947918891906738,
+      "rewards/rejected": -3.6618781089782715,
+      "step": 450
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 26.40697406008373,
+      "learning_rate": 2.158697848236607e-09,
+      "logits/chosen": -0.5525180697441101,
+      "logits/rejected": 0.4095240533351898,
+      "logps/chosen": -521.8342895507812,
+      "logps/rejected": -599.0489501953125,
+      "loss": 0.4933,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -2.4641835689544678,
+      "rewards/margins": 1.049481987953186,
+      "rewards/rejected": -3.5136656761169434,
+      "step": 460
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 40.87484210645662,
+      "learning_rate": 4.269029751107489e-10,
+      "logits/chosen": -0.38540196418762207,
+      "logits/rejected": 0.25467342138290405,
+      "logps/chosen": -550.1776123046875,
+      "logps/rejected": -633.5750732421875,
+      "loss": 0.4908,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -2.6054952144622803,
+      "rewards/margins": 0.973294734954834,
+      "rewards/rejected": -3.5787901878356934,
+      "step": 470
+    },
+    {
+      "epoch": 1.0,
+      "step": 478,
+      "total_flos": 0.0,
+      "train_loss": 0.535196884905444,
+      "train_runtime": 3527.4214,
+      "train_samples_per_second": 17.331,
+      "train_steps_per_second": 0.136
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 478,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}