Model save

README.md

@@ -0,0 +1,74 @@
+---
+base_model: Minbyul/selfbiorag-7b-wo-live_qa-sft
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: selfbiorag-7b-dpo-full-sft-wo-live_qa
+  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. -->
+
+# selfbiorag-7b-dpo-full-sft-wo-live_qa
+
+This model is a fine-tuned version of [Minbyul/selfbiorag-7b-wo-live_qa-sft](https://huggingface.co/Minbyul/selfbiorag-7b-wo-live_qa-sft) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1421
+- Rewards/chosen: -1.2604
+- Rewards/rejected: -13.2286
+- Rewards/accuracies: 0.9167
+- Rewards/margins: 11.9683
+- Logps/rejected: -1987.8828
+- Logps/chosen: -455.8129
+- Logits/rejected: -0.4048
+- Logits/chosen: -0.4887
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- 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_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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.2635        | 0.3   | 100  | 0.1990          | -0.5114        | -9.8179          | 0.9167             | 9.3065          | -1646.8138     | -380.9204    | -0.1085         | -0.3091       |
+| 0.1415        | 0.61  | 200  | 0.1502          | -0.9081        | -11.0651         | 0.9167             | 10.1570         | -1771.5302     | -420.5836    | -0.4280         | -0.4824       |
+| 0.0892        | 0.91  | 300  | 0.1421          | -1.2604        | -13.2286         | 0.9167             | 11.9683         | -1987.8828     | -455.8129    | -0.4048         | -0.4887       |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.22599055091055428,
+    "train_runtime": 7017.6011,
+    "train_samples": 20961,
+    "train_samples_per_second": 2.987,
+    "train_steps_per_second": 0.047
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56789e18bcac8612aa5a6f95b483e0b5779cfc7ba6e377dd822bd5d077cf056
+size 4939116424

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58bcc786bda5802f3cb091c999b7223b0a0cd2fa67c284c8e8dfc4ad3dba635f
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257072fdcbd91683f3c6caade4b95541e57b474e227c9fc7a0bc2aa524680737
+size 3590619888

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13477093376
+  },
+  "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-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-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-00001-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-00001-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-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-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-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-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-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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": 1.0,
+    "train_loss": 0.22599055091055428,
+    "train_runtime": 7017.6011,
+    "train_samples": 20961,
+    "train_samples_per_second": 2.987,
+    "train_steps_per_second": 0.047
+}

trainer_state.json

@@ -0,0 +1,573 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 328,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.561485449698178,
+      "learning_rate": 1.5151515151515152e-07,
+      "logits/chosen": -0.4639463722705841,
+      "logits/rejected": -0.17450889945030212,
+      "logps/chosen": -612.9666748046875,
+      "logps/rejected": -1227.4912109375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.576753539954733,
+      "learning_rate": 1.5151515151515152e-06,
+      "logits/chosen": -0.41454941034317017,
+      "logits/rejected": -0.577505350112915,
+      "logps/chosen": -869.0648803710938,
+      "logps/rejected": -1276.6817626953125,
+      "loss": 0.6913,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.0039122202433645725,
+      "rewards/margins": 0.003580428659915924,
+      "rewards/rejected": -0.007492648903280497,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.198667632843589,
+      "learning_rate": 3.0303030303030305e-06,
+      "logits/chosen": -0.3819029927253723,
+      "logits/rejected": -0.46113020181655884,
+      "logps/chosen": -997.2161865234375,
+      "logps/rejected": -1214.39990234375,
+      "loss": 0.6612,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": -0.15533407032489777,
+      "rewards/margins": 0.047475699335336685,
+      "rewards/rejected": -0.20280976593494415,
+      "step": 20
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.889725033116788,
+      "learning_rate": 4.5454545454545455e-06,
+      "logits/chosen": -0.24505889415740967,
+      "logits/rejected": -0.24203690886497498,
+      "logps/chosen": -911.0994873046875,
+      "logps/rejected": -1363.7496337890625,
+      "loss": 0.541,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.39497110247612,
+      "rewards/margins": 0.5585557222366333,
+      "rewards/rejected": -0.9535268545150757,
+      "step": 30
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.086637897535325,
+      "learning_rate": 4.9930567839810125e-06,
+      "logits/chosen": -0.17689356207847595,
+      "logits/rejected": -0.16114920377731323,
+      "logps/chosen": -1011.1546630859375,
+      "logps/rejected": -1480.3541259765625,
+      "loss": 0.4484,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.3060458302497864,
+      "rewards/margins": 1.0700631141662598,
+      "rewards/rejected": -1.3761091232299805,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.522119109661391,
+      "learning_rate": 4.959142005221991e-06,
+      "logits/chosen": -0.11198903620243073,
+      "logits/rejected": -0.15591135621070862,
+      "logps/chosen": -899.4259033203125,
+      "logps/rejected": -1485.4820556640625,
+      "loss": 0.4169,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.2616763412952423,
+      "rewards/margins": 1.9235137701034546,
+      "rewards/rejected": -2.185190439224243,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.555413111169151,
+      "learning_rate": 4.897364164920515e-06,
+      "logits/chosen": -0.1413438618183136,
+      "logits/rejected": -0.248577281832695,
+      "logps/chosen": -856.3390502929688,
+      "logps/rejected": -1524.873291015625,
+      "loss": 0.3649,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.2767874300479889,
+      "rewards/margins": 1.9685882329940796,
+      "rewards/rejected": -2.245375871658325,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.814409469094451,
+      "learning_rate": 4.808423230692374e-06,
+      "logits/chosen": -0.23499484360218048,
+      "logits/rejected": -0.3045286536216736,
+      "logps/chosen": -930.0250854492188,
+      "logps/rejected": -1563.339599609375,
+      "loss": 0.3102,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.22926001250743866,
+      "rewards/margins": 2.3029136657714844,
+      "rewards/rejected": -2.5321736335754395,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.080973924268642,
+      "learning_rate": 4.693326938861367e-06,
+      "logits/chosen": -0.19219891726970673,
+      "logits/rejected": -0.29335862398147583,
+      "logps/chosen": -1067.5966796875,
+      "logps/rejected": -1646.7294921875,
+      "loss": 0.3024,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": -0.3816714882850647,
+      "rewards/margins": 2.590569019317627,
+      "rewards/rejected": -2.972240447998047,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 4.198144592019097,
+      "learning_rate": 4.553379376404085e-06,
+      "logits/chosen": -0.16756731271743774,
+      "logits/rejected": -0.2766783535480499,
+      "logps/chosen": -901.4991455078125,
+      "logps/rejected": -1794.3072509765625,
+      "loss": 0.249,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.32676273584365845,
+      "rewards/margins": 4.70559549331665,
+      "rewards/rejected": -5.032357215881348,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.514239110297717,
+      "learning_rate": 4.3901662051233755e-06,
+      "logits/chosen": -0.13113151490688324,
+      "logits/rejected": -0.23850134015083313,
+      "logps/chosen": -943.93701171875,
+      "logps/rejected": -1710.283203125,
+      "loss": 0.2635,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": -0.5341259837150574,
+      "rewards/margins": 4.174313545227051,
+      "rewards/rejected": -4.708439826965332,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "eval_logits/chosen": -0.3091484606266022,
+      "eval_logits/rejected": -0.10848761349916458,
+      "eval_logps/chosen": -380.92041015625,
+      "eval_logps/rejected": -1646.8138427734375,
+      "eval_loss": 0.199021577835083,
+      "eval_rewards/accuracies": 0.9166666865348816,
+      "eval_rewards/chosen": -0.5114283561706543,
+      "eval_rewards/margins": 9.306483268737793,
+      "eval_rewards/rejected": -9.817912101745605,
+      "eval_runtime": 29.898,
+      "eval_samples_per_second": 6.422,
+      "eval_steps_per_second": 0.201,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.7779512658548504,
+      "learning_rate": 4.205536695466524e-06,
+      "logits/chosen": -0.13202831149101257,
+      "logits/rejected": -0.31658726930618286,
+      "logps/chosen": -881.8616333007812,
+      "logps/rejected": -1843.311767578125,
+      "loss": 0.2265,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.4379568099975586,
+      "rewards/margins": 4.332350254058838,
+      "rewards/rejected": -4.7703070640563965,
+      "step": 110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.058731694797242,
+      "learning_rate": 4.001582773552153e-06,
+      "logits/chosen": -0.2267748862504959,
+      "logits/rejected": -0.37614327669143677,
+      "logps/chosen": -1021.9287109375,
+      "logps/rejected": -1790.741455078125,
+      "loss": 0.2448,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": -0.7997490167617798,
+      "rewards/margins": 3.615135908126831,
+      "rewards/rejected": -4.4148850440979,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.5646553088179957,
+      "learning_rate": 3.7806153188114027e-06,
+      "logits/chosen": -0.14952275156974792,
+      "logits/rejected": -0.26807302236557007,
+      "logps/chosen": -988.8695068359375,
+      "logps/rejected": -1687.877197265625,
+      "loss": 0.199,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -0.5245489478111267,
+      "rewards/margins": 2.954119920730591,
+      "rewards/rejected": -3.4786689281463623,
+      "step": 130
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.994600163477232,
+      "learning_rate": 3.5451379808006014e-06,
+      "logits/chosen": -0.1331457495689392,
+      "logits/rejected": -0.23687326908111572,
+      "logps/chosen": -885.8282470703125,
+      "logps/rejected": -1685.4974365234375,
+      "loss": 0.2011,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": -0.609821617603302,
+      "rewards/margins": 3.710085391998291,
+      "rewards/rejected": -4.319907188415527,
+      "step": 140
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.000160476158621,
+      "learning_rate": 3.2978188118513814e-06,
+      "logits/chosen": -0.13606548309326172,
+      "logits/rejected": -0.32709023356437683,
+      "logps/chosen": -931.5257568359375,
+      "logps/rejected": -1801.125,
+      "loss": 0.1791,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -0.4420163631439209,
+      "rewards/margins": 4.814242362976074,
+      "rewards/rejected": -5.256258964538574,
+      "step": 150
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 5.561015522393931,
+      "learning_rate": 3.041460036971664e-06,
+      "logits/chosen": -0.20122027397155762,
+      "logits/rejected": -0.37438589334487915,
+      "logps/chosen": -960.2258911132812,
+      "logps/rejected": -1840.1077880859375,
+      "loss": 0.1646,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.548378050327301,
+      "rewards/margins": 5.22580623626709,
+      "rewards/rejected": -5.774184703826904,
+      "step": 160
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.0160283224172506,
+      "learning_rate": 2.7789663035166035e-06,
+      "logits/chosen": -0.2793598771095276,
+      "logits/rejected": -0.4746064245700836,
+      "logps/chosen": -1049.3095703125,
+      "logps/rejected": -1993.3609619140625,
+      "loss": 0.1263,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -0.5465644598007202,
+      "rewards/margins": 6.312196731567383,
+      "rewards/rejected": -6.858761787414551,
+      "step": 170
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.93594175440836,
+      "learning_rate": 2.513311770373421e-06,
+      "logits/chosen": -0.31422796845436096,
+      "logits/rejected": -0.5171582102775574,
+      "logps/chosen": -960.77978515625,
+      "logps/rejected": -1946.6195068359375,
+      "loss": 0.1157,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": -0.6941060423851013,
+      "rewards/margins": 5.883716583251953,
+      "rewards/rejected": -6.577822685241699,
+      "step": 180
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.989156252845766,
+      "learning_rate": 2.247506409552795e-06,
+      "logits/chosen": -0.3567090332508087,
+      "logits/rejected": -0.5727603435516357,
+      "logps/chosen": -1111.8785400390625,
+      "logps/rejected": -2083.59716796875,
+      "loss": 0.1418,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.5756088495254517,
+      "rewards/margins": 6.701145172119141,
+      "rewards/rejected": -7.276753902435303,
+      "step": 190
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 3.220493331131803,
+      "learning_rate": 1.9845619020032552e-06,
+      "logits/chosen": -0.4283437132835388,
+      "logits/rejected": -0.6103153228759766,
+      "logps/chosen": -977.1068115234375,
+      "logps/rejected": -1989.1517333984375,
+      "loss": 0.1415,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -0.26823538541793823,
+      "rewards/margins": 6.212519645690918,
+      "rewards/rejected": -6.480755805969238,
+      "step": 200
+    },
+    {
+      "epoch": 0.61,
+      "eval_logits/chosen": -0.48242926597595215,
+      "eval_logits/rejected": -0.42804303765296936,
+      "eval_logps/chosen": -420.5835876464844,
+      "eval_logps/rejected": -1771.5301513671875,
+      "eval_loss": 0.15017390251159668,
+      "eval_rewards/accuracies": 0.9166666865348816,
+      "eval_rewards/chosen": -0.9080603122711182,
+      "eval_rewards/margins": 10.157015800476074,
+      "eval_rewards/rejected": -11.065074920654297,
+      "eval_runtime": 29.9491,
+      "eval_samples_per_second": 6.411,
+      "eval_steps_per_second": 0.2,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.03992800632795,
+      "learning_rate": 1.7274575140626318e-06,
+      "logits/chosen": -0.40144267678260803,
+      "logits/rejected": -0.6470441818237305,
+      "logps/chosen": -992.0281372070312,
+      "logps/rejected": -1956.958984375,
+      "loss": 0.1581,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": -0.683698832988739,
+      "rewards/margins": 6.963919162750244,
+      "rewards/rejected": -7.647618293762207,
+      "step": 210
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.5930618000995724,
+      "learning_rate": 1.4791063411799938e-06,
+      "logits/chosen": -0.4398053288459778,
+      "logits/rejected": -0.6155021786689758,
+      "logps/chosen": -901.8489990234375,
+      "logps/rejected": -1997.6116943359375,
+      "loss": 0.1258,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.4012775421142578,
+      "rewards/margins": 6.776458740234375,
+      "rewards/rejected": -7.177737236022949,
+      "step": 220
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.126671458993684,
+      "learning_rate": 1.2423223013801946e-06,
+      "logits/chosen": -0.4161323606967926,
+      "logits/rejected": -0.6325975656509399,
+      "logps/chosen": -993.7923583984375,
+      "logps/rejected": -2073.91064453125,
+      "loss": 0.1237,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.23834288120269775,
+      "rewards/margins": 6.739261627197266,
+      "rewards/rejected": -6.977604866027832,
+      "step": 230
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.053249955458482,
+      "learning_rate": 1.019788252448267e-06,
+      "logits/chosen": -0.41894397139549255,
+      "logits/rejected": -0.5673054456710815,
+      "logps/chosen": -946.7174682617188,
+      "logps/rejected": -2171.60009765625,
+      "loss": 0.0947,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -0.34920141100883484,
+      "rewards/margins": 8.334190368652344,
+      "rewards/rejected": -8.683391571044922,
+      "step": 240
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.2492894915267074,
+      "learning_rate": 8.140255940787059e-07,
+      "logits/chosen": -0.4345846176147461,
+      "logits/rejected": -0.5576716661453247,
+      "logps/chosen": -990.5559692382812,
+      "logps/rejected": -2134.9990234375,
+      "loss": 0.1116,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -0.7247036695480347,
+      "rewards/margins": 7.789909362792969,
+      "rewards/rejected": -8.514613151550293,
+      "step": 250
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.064615334983041,
+      "learning_rate": 6.273656994094232e-07,
+      "logits/chosen": -0.4094814658164978,
+      "logits/rejected": -0.6032238006591797,
+      "logps/chosen": -973.67041015625,
+      "logps/rejected": -2180.19677734375,
+      "loss": 0.1092,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": -0.7021085023880005,
+      "rewards/margins": 8.40003776550293,
+      "rewards/rejected": -9.102147102355957,
+      "step": 260
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.2441288839699647,
+      "learning_rate": 4.619234996325314e-07,
+      "logits/chosen": -0.4224594235420227,
+      "logits/rejected": -0.5946496725082397,
+      "logps/chosen": -1018.1749267578125,
+      "logps/rejected": -2218.16552734375,
+      "loss": 0.0905,
+      "rewards/accuracies": 0.981249988079071,
+      "rewards/chosen": -0.5338882803916931,
+      "rewards/margins": 8.705224990844727,
+      "rewards/rejected": -9.23911190032959,
+      "step": 270
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.0256681132412035,
+      "learning_rate": 3.195735209788528e-07,
+      "logits/chosen": -0.37011057138442993,
+      "logits/rejected": -0.6081669330596924,
+      "logps/chosen": -967.2252197265625,
+      "logps/rejected": -2145.68798828125,
+      "loss": 0.1005,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.7551916837692261,
+      "rewards/margins": 7.838353157043457,
+      "rewards/rejected": -8.593544960021973,
+      "step": 280
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.259685670607253,
+      "learning_rate": 2.019286455866981e-07,
+      "logits/chosen": -0.41176638007164,
+      "logits/rejected": -0.5948176980018616,
+      "logps/chosen": -1099.498779296875,
+      "logps/rejected": -2072.706298828125,
+      "loss": 0.1126,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": -0.7403249740600586,
+      "rewards/margins": 6.6156768798828125,
+      "rewards/rejected": -7.356001853942871,
+      "step": 290
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.837717904545823,
+      "learning_rate": 1.1032183690276754e-07,
+      "logits/chosen": -0.38978689908981323,
+      "logits/rejected": -0.554754376411438,
+      "logps/chosen": -1006.9293212890625,
+      "logps/rejected": -2237.94970703125,
+      "loss": 0.0892,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.7637746334075928,
+      "rewards/margins": 8.33720874786377,
+      "rewards/rejected": -9.100981712341309,
+      "step": 300
+    },
+    {
+      "epoch": 0.91,
+      "eval_logits/chosen": -0.48870301246643066,
+      "eval_logits/rejected": -0.40482982993125916,
+      "eval_logps/chosen": -455.8128662109375,
+      "eval_logps/rejected": -1987.8828125,
+      "eval_loss": 0.14211897552013397,
+      "eval_rewards/accuracies": 0.9166666865348816,
+      "eval_rewards/chosen": -1.2603524923324585,
+      "eval_rewards/margins": 11.968250274658203,
+      "eval_rewards/rejected": -13.228604316711426,
+      "eval_runtime": 29.6183,
+      "eval_samples_per_second": 6.482,
+      "eval_steps_per_second": 0.203,
+      "step": 300
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 2.6436300030745867,
+      "learning_rate": 4.579103667367385e-08,
+      "logits/chosen": -0.4472607672214508,
+      "logits/rejected": -0.6000027656555176,
+      "logps/chosen": -1035.2442626953125,
+      "logps/rejected": -2228.332275390625,
+      "loss": 0.1212,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": -0.6586896777153015,
+      "rewards/margins": 9.017664909362793,
+      "rewards/rejected": -9.676355361938477,
+      "step": 310
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.053048154617744,
+      "learning_rate": 9.067404651211808e-09,
+      "logits/chosen": -0.42106541991233826,
+      "logits/rejected": -0.5793359279632568,
+      "logps/chosen": -992.0040283203125,
+      "logps/rejected": -2126.542724609375,
+      "loss": 0.0966,
+      "rewards/accuracies": 0.9750000238418579,
+      "rewards/chosen": -0.767730176448822,
+      "rewards/margins": 8.566682815551758,
+      "rewards/rejected": -9.334413528442383,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "step": 328,
+      "total_flos": 0.0,
+      "train_loss": 0.22599055091055428,
+      "train_runtime": 7017.6011,
+      "train_samples_per_second": 2.987,
+      "train_steps_per_second": 0.047
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 328,
+  "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
+}