Model save

README.md

@@ -0,0 +1,74 @@
+---
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-dpo-full-accumulation4
+  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-accumulation4
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5042
+- Rewards/chosen: -1.0384
+- Rewards/rejected: -2.0520
+- Rewards/accuracies: 0.7773
+- Rewards/margins: 1.0136
+- Logps/rejected: -465.5701
+- Logps/chosen: -363.5876
+- Logits/rejected: 3.4727
+- Logits/chosen: 2.9519
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.59          | 0.2093 | 100  | 0.5946          | -0.2826        | -0.6651          | 0.7266             | 0.3825          | -326.8777      | -288.0025    | -2.2764         | -2.3187       |
+| 0.5622        | 0.4186 | 200  | 0.5490          | -0.5914        | -1.2367          | 0.7578             | 0.6452          | -384.0357      | -318.8896    | -1.6885         | -1.7635       |
+| 0.5069        | 0.6279 | 300  | 0.5186          | -0.9189        | -1.8568          | 0.7773             | 0.9379          | -446.0468      | -351.6352    | 3.7286          | 3.1924        |
+| 0.5183        | 0.8373 | 400  | 0.5042          | -1.0384        | -2.0520          | 0.7773             | 1.0136          | -465.5701      | -363.5876    | 3.4727          | 2.9519        |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9984301412872841,
+    "total_flos": 0.0,
+    "train_loss": 0.5498417743346976,
+    "train_runtime": 10726.7175,
+    "train_samples": 61134,
+    "train_samples_per_second": 5.699,
+    "train_steps_per_second": 0.044
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78aa98606292790d96bdb9e38b3777f58cc242bfd663a6dd42e2bef657aeafe3
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1544365cf12e9b90147a26be2961ac42606831f59080cd2acb2f73399b236e99
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f76d129c37b9f9db0670457cb7040823514642b7ed173575b594924568c65e8
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9984301412872841,
+    "total_flos": 0.0,
+    "train_loss": 0.5498417743346976,
+    "train_runtime": 10726.7175,
+    "train_samples": 61134,
+    "train_samples_per_second": 5.699,
+    "train_steps_per_second": 0.044
+}

trainer_state.json

@@ -0,0 +1,814 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984301412872841,
+  "eval_steps": 100,
+  "global_step": 477,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020931449502878076,
+      "grad_norm": 9.701703889717688,
+      "learning_rate": 1.0416666666666666e-08,
+      "logits/chosen": -2.6944541931152344,
+      "logits/rejected": -2.6506383419036865,
+      "logps/chosen": -310.44775390625,
+      "logps/rejected": -356.37457275390625,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.020931449502878074,
+      "grad_norm": 8.84546269100533,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -2.4350545406341553,
+      "logits/rejected": -2.4006903171539307,
+      "logps/chosen": -303.82672119140625,
+      "logps/rejected": -273.402099609375,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.4236111044883728,
+      "rewards/chosen": -0.00024138028675224632,
+      "rewards/margins": -0.00029328116215765476,
+      "rewards/rejected": 5.190089359530248e-05,
+      "step": 10
+    },
+    {
+      "epoch": 0.04186289900575615,
+      "grad_norm": 7.848621492291795,
+      "learning_rate": 2.0833333333333333e-07,
+      "logits/chosen": -2.5433900356292725,
+      "logits/rejected": -2.46927809715271,
+      "logps/chosen": -304.30694580078125,
+      "logps/rejected": -278.98370361328125,
+      "loss": 0.6924,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": 0.0008761318167671561,
+      "rewards/margins": 0.0014354921877384186,
+      "rewards/rejected": -0.0005593602545559406,
+      "step": 20
+    },
+    {
+      "epoch": 0.06279434850863422,
+      "grad_norm": 7.994491246894057,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -2.508960723876953,
+      "logits/rejected": -2.4349305629730225,
+      "logps/chosen": -283.6884460449219,
+      "logps/rejected": -244.4142608642578,
+      "loss": 0.6897,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.01013423502445221,
+      "rewards/margins": 0.00718701770529151,
+      "rewards/rejected": 0.0029472168534994125,
+      "step": 30
+    },
+    {
+      "epoch": 0.0837257980115123,
+      "grad_norm": 8.14200571971664,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -2.394131898880005,
+      "logits/rejected": -2.3530144691467285,
+      "logps/chosen": -263.22686767578125,
+      "logps/rejected": -257.85711669921875,
+      "loss": 0.6805,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": 0.02391662448644638,
+      "rewards/margins": 0.026386350393295288,
+      "rewards/rejected": -0.0024697293993085623,
+      "step": 40
+    },
+    {
+      "epoch": 0.10465724751439037,
+      "grad_norm": 11.105720053216691,
+      "learning_rate": 4.999731868769026e-07,
+      "logits/chosen": -2.449319362640381,
+      "logits/rejected": -2.371795654296875,
+      "logps/chosen": -272.06561279296875,
+      "logps/rejected": -272.468505859375,
+      "loss": 0.6687,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.019743364304304123,
+      "rewards/margins": 0.04323229938745499,
+      "rewards/rejected": -0.023488933220505714,
+      "step": 50
+    },
+    {
+      "epoch": 0.12558869701726844,
+      "grad_norm": 10.342921474048731,
+      "learning_rate": 4.990353313429303e-07,
+      "logits/chosen": -2.4817090034484863,
+      "logits/rejected": -2.4134628772735596,
+      "logps/chosen": -252.6865997314453,
+      "logps/rejected": -255.49368286132812,
+      "loss": 0.6474,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.011149518191814423,
+      "rewards/margins": 0.11335233598947525,
+      "rewards/rejected": -0.12450186163187027,
+      "step": 60
+    },
+    {
+      "epoch": 0.14652014652014653,
+      "grad_norm": 11.35307919444153,
+      "learning_rate": 4.967625656594781e-07,
+      "logits/chosen": -2.40004825592041,
+      "logits/rejected": -2.3668346405029297,
+      "logps/chosen": -293.5352478027344,
+      "logps/rejected": -296.67926025390625,
+      "loss": 0.6252,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -0.030240410938858986,
+      "rewards/margins": 0.16815462708473206,
+      "rewards/rejected": -0.1983950436115265,
+      "step": 70
+    },
+    {
+      "epoch": 0.1674515960230246,
+      "grad_norm": 12.734807020264979,
+      "learning_rate": 4.93167072587771e-07,
+      "logits/chosen": -2.4908807277679443,
+      "logits/rejected": -2.381664991378784,
+      "logps/chosen": -342.2506408691406,
+      "logps/rejected": -293.37591552734375,
+      "loss": 0.6095,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.13335664570331573,
+      "rewards/margins": 0.2423185110092163,
+      "rewards/rejected": -0.37567517161369324,
+      "step": 80
+    },
+    {
+      "epoch": 0.18838304552590268,
+      "grad_norm": 15.61185554124782,
+      "learning_rate": 4.882681251368548e-07,
+      "logits/chosen": -2.4205806255340576,
+      "logits/rejected": -2.3800764083862305,
+      "logps/chosen": -292.38299560546875,
+      "logps/rejected": -330.5673828125,
+      "loss": 0.5879,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.4269022047519684,
+      "rewards/margins": 0.3442407548427582,
+      "rewards/rejected": -0.7711430191993713,
+      "step": 90
+    },
+    {
+      "epoch": 0.20931449502878074,
+      "grad_norm": 13.322347449232225,
+      "learning_rate": 4.820919832540181e-07,
+      "logits/chosen": -2.354395627975464,
+      "logits/rejected": -2.276475667953491,
+      "logps/chosen": -347.62921142578125,
+      "logps/rejected": -368.50421142578125,
+      "loss": 0.59,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.5006760954856873,
+      "rewards/margins": 0.4406515657901764,
+      "rewards/rejected": -0.941327691078186,
+      "step": 100
+    },
+    {
+      "epoch": 0.20931449502878074,
+      "eval_logits/chosen": -2.318732500076294,
+      "eval_logits/rejected": -2.276435613632202,
+      "eval_logps/chosen": -288.0024719238281,
+      "eval_logps/rejected": -326.8777160644531,
+      "eval_loss": 0.5945977568626404,
+      "eval_rewards/accuracies": 0.7265625,
+      "eval_rewards/chosen": -0.282560259103775,
+      "eval_rewards/margins": 0.3825291395187378,
+      "eval_rewards/rejected": -0.6650894284248352,
+      "eval_runtime": 135.0162,
+      "eval_samples_per_second": 14.813,
+      "eval_steps_per_second": 0.237,
+      "step": 100
+    },
+    {
+      "epoch": 0.2302459445316588,
+      "grad_norm": 16.09917423674647,
+      "learning_rate": 4.7467175306295647e-07,
+      "logits/chosen": -2.338008165359497,
+      "logits/rejected": -2.2681479454040527,
+      "logps/chosen": -322.53961181640625,
+      "logps/rejected": -342.4386901855469,
+      "loss": 0.592,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.3449268043041229,
+      "rewards/margins": 0.3611523509025574,
+      "rewards/rejected": -0.7060791254043579,
+      "step": 110
+    },
+    {
+      "epoch": 0.25117739403453687,
+      "grad_norm": 14.762649607127566,
+      "learning_rate": 4.6604720940421207e-07,
+      "logits/chosen": -2.2040162086486816,
+      "logits/rejected": -2.1983416080474854,
+      "logps/chosen": -316.65032958984375,
+      "logps/rejected": -354.5749206542969,
+      "loss": 0.5633,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.4746555685997009,
+      "rewards/margins": 0.4826603829860687,
+      "rewards/rejected": -0.9573159217834473,
+      "step": 120
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 15.498777786824567,
+      "learning_rate": 4.5626458262912735e-07,
+      "logits/chosen": -2.2507164478302,
+      "logits/rejected": -2.219001531600952,
+      "logps/chosen": -349.1249084472656,
+      "logps/rejected": -375.2015686035156,
+      "loss": 0.5545,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6135660409927368,
+      "rewards/margins": 0.4482480585575104,
+      "rewards/rejected": -1.0618140697479248,
+      "step": 130
+    },
+    {
+      "epoch": 0.29304029304029305,
+      "grad_norm": 19.626416480852797,
+      "learning_rate": 4.453763107901675e-07,
+      "logits/chosen": -2.2545251846313477,
+      "logits/rejected": -2.190607786178589,
+      "logps/chosen": -360.6560974121094,
+      "logps/rejected": -375.7515563964844,
+      "loss": 0.5624,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -0.4800276756286621,
+      "rewards/margins": 0.6141252517700195,
+      "rewards/rejected": -1.094152808189392,
+      "step": 140
+    },
+    {
+      "epoch": 0.3139717425431711,
+      "grad_norm": 18.096131162027284,
+      "learning_rate": 4.3344075855595097e-07,
+      "logits/chosen": -2.1750240325927734,
+      "logits/rejected": -2.100369453430176,
+      "logps/chosen": -335.5732421875,
+      "logps/rejected": -344.1123352050781,
+      "loss": 0.5645,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.5581367611885071,
+      "rewards/margins": 0.4194498658180237,
+      "rewards/rejected": -0.9775866270065308,
+      "step": 150
+    },
+    {
+      "epoch": 0.3349031920460492,
+      "grad_norm": 18.25363304753259,
+      "learning_rate": 4.2052190435769554e-07,
+      "logits/chosen": -2.1590893268585205,
+      "logits/rejected": -2.0513908863067627,
+      "logps/chosen": -333.60272216796875,
+      "logps/rejected": -363.22113037109375,
+      "loss": 0.5666,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.6136575937271118,
+      "rewards/margins": 0.5171821117401123,
+      "rewards/rejected": -1.1308397054672241,
+      "step": 160
+    },
+    {
+      "epoch": 0.35583464154892724,
+      "grad_norm": 19.640735202416472,
+      "learning_rate": 4.0668899744407567e-07,
+      "logits/chosen": -1.902665376663208,
+      "logits/rejected": -1.8501911163330078,
+      "logps/chosen": -327.90606689453125,
+      "logps/rejected": -346.9702453613281,
+      "loss": 0.5614,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.7038865089416504,
+      "rewards/margins": 0.4166206419467926,
+      "rewards/rejected": -1.1205071210861206,
+      "step": 170
+    },
+    {
+      "epoch": 0.37676609105180536,
+      "grad_norm": 17.690184861626957,
+      "learning_rate": 3.920161866827889e-07,
+      "logits/chosen": -1.8513147830963135,
+      "logits/rejected": -1.7969615459442139,
+      "logps/chosen": -333.0622253417969,
+      "logps/rejected": -355.8721618652344,
+      "loss": 0.5267,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.6485015153884888,
+      "rewards/margins": 0.492420494556427,
+      "rewards/rejected": -1.140921950340271,
+      "step": 180
+    },
+    {
+      "epoch": 0.3976975405546834,
+      "grad_norm": 17.575830552485073,
+      "learning_rate": 3.765821230985757e-07,
+      "logits/chosen": -1.7381349802017212,
+      "logits/rejected": -1.7155596017837524,
+      "logps/chosen": -314.037353515625,
+      "logps/rejected": -358.69110107421875,
+      "loss": 0.5472,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -0.586374819278717,
+      "rewards/margins": 0.4954743981361389,
+      "rewards/rejected": -1.0818490982055664,
+      "step": 190
+    },
+    {
+      "epoch": 0.4186289900575615,
+      "grad_norm": 20.16868358579315,
+      "learning_rate": 3.604695382782159e-07,
+      "logits/chosen": -1.6889305114746094,
+      "logits/rejected": -1.671118974685669,
+      "logps/chosen": -314.1725158691406,
+      "logps/rejected": -383.7921142578125,
+      "loss": 0.5622,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.650070071220398,
+      "rewards/margins": 0.5007017254829407,
+      "rewards/rejected": -1.1507718563079834,
+      "step": 200
+    },
+    {
+      "epoch": 0.4186289900575615,
+      "eval_logits/chosen": -1.763492226600647,
+      "eval_logits/rejected": -1.688451886177063,
+      "eval_logps/chosen": -318.8896484375,
+      "eval_logps/rejected": -384.0356750488281,
+      "eval_loss": 0.5489535927772522,
+      "eval_rewards/accuracies": 0.7578125,
+      "eval_rewards/chosen": -0.5914322733879089,
+      "eval_rewards/margins": 0.6452370285987854,
+      "eval_rewards/rejected": -1.2366693019866943,
+      "eval_runtime": 135.851,
+      "eval_samples_per_second": 14.722,
+      "eval_steps_per_second": 0.236,
+      "step": 200
+    },
+    {
+      "epoch": 0.43956043956043955,
+      "grad_norm": 22.253978043488576,
+      "learning_rate": 3.4376480090239047e-07,
+      "logits/chosen": -1.7683002948760986,
+      "logits/rejected": -1.5815565586090088,
+      "logps/chosen": -374.9300231933594,
+      "logps/rejected": -366.38726806640625,
+      "loss": 0.5621,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.6777712106704712,
+      "rewards/margins": 0.5172096490859985,
+      "rewards/rejected": -1.1949809789657593,
+      "step": 210
+    },
+    {
+      "epoch": 0.4604918890633176,
+      "grad_norm": 25.258798608949323,
+      "learning_rate": 3.265574537815398e-07,
+      "logits/chosen": -1.1447908878326416,
+      "logits/rejected": -1.011715054512024,
+      "logps/chosen": -310.7139892578125,
+      "logps/rejected": -368.12908935546875,
+      "loss": 0.5493,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.7031707763671875,
+      "rewards/margins": 0.5581351518630981,
+      "rewards/rejected": -1.2613059282302856,
+      "step": 220
+    },
+    {
+      "epoch": 0.48142333856619574,
+      "grad_norm": 20.0981990151217,
+      "learning_rate": 3.0893973387735683e-07,
+      "logits/chosen": -0.7348424792289734,
+      "logits/rejected": -0.39249858260154724,
+      "logps/chosen": -343.92913818359375,
+      "logps/rejected": -406.53704833984375,
+      "loss": 0.5497,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.8420748710632324,
+      "rewards/margins": 0.8347824811935425,
+      "rewards/rejected": -1.676857352256775,
+      "step": 230
+    },
+    {
+      "epoch": 0.5023547880690737,
+      "grad_norm": 23.111675146594926,
+      "learning_rate": 2.910060778827554e-07,
+      "logits/chosen": -0.2739952504634857,
+      "logits/rejected": 0.06540920585393906,
+      "logps/chosen": -362.68609619140625,
+      "logps/rejected": -405.169921875,
+      "loss": 0.517,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.7693260908126831,
+      "rewards/margins": 0.6784046292304993,
+      "rewards/rejected": -1.4477307796478271,
+      "step": 240
+    },
+    {
+      "epoch": 0.5232862375719518,
+      "grad_norm": 23.369631676215544,
+      "learning_rate": 2.7285261601056697e-07,
+      "logits/chosen": 0.34806543588638306,
+      "logits/rejected": 0.8901464343070984,
+      "logps/chosen": -355.3818054199219,
+      "logps/rejected": -410.10003662109375,
+      "loss": 0.5287,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -0.8285034894943237,
+      "rewards/margins": 0.8582339286804199,
+      "rewards/rejected": -1.6867374181747437,
+      "step": 250
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 29.7084865691872,
+      "learning_rate": 2.5457665670441937e-07,
+      "logits/chosen": 1.2245562076568604,
+      "logits/rejected": 1.454952597618103,
+      "logps/chosen": -350.949462890625,
+      "logps/rejected": -401.76385498046875,
+      "loss": 0.5176,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.9003115892410278,
+      "rewards/margins": 0.6968273520469666,
+      "rewards/rejected": -1.5971391201019287,
+      "step": 260
+    },
+    {
+      "epoch": 0.565149136577708,
+      "grad_norm": 22.876027469847745,
+      "learning_rate": 2.3627616503391812e-07,
+      "logits/chosen": 1.6951497793197632,
+      "logits/rejected": 2.2218925952911377,
+      "logps/chosen": -372.63812255859375,
+      "logps/rejected": -434.4366760253906,
+      "loss": 0.5252,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.8350957632064819,
+      "rewards/margins": 0.8779489398002625,
+      "rewards/rejected": -1.7130447626113892,
+      "step": 270
+    },
+    {
+      "epoch": 0.5860805860805861,
+      "grad_norm": 24.484724598276838,
+      "learning_rate": 2.1804923757009882e-07,
+      "logits/chosen": 2.2372639179229736,
+      "logits/rejected": 2.9480350017547607,
+      "logps/chosen": -346.4819641113281,
+      "logps/rejected": -377.4454650878906,
+      "loss": 0.5341,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.8397897481918335,
+      "rewards/margins": 0.6329924464225769,
+      "rewards/rejected": -1.4727823734283447,
+      "step": 280
+    },
+    {
+      "epoch": 0.6070120355834642,
+      "grad_norm": 29.638756278748712,
+      "learning_rate": 1.9999357655598891e-07,
+      "logits/chosen": 2.36271595954895,
+      "logits/rejected": 2.822075605392456,
+      "logps/chosen": -325.40875244140625,
+      "logps/rejected": -398.14703369140625,
+      "loss": 0.5234,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.7926238775253296,
+      "rewards/margins": 0.7679665684700012,
+      "rewards/rejected": -1.5605905055999756,
+      "step": 290
+    },
+    {
+      "epoch": 0.6279434850863422,
+      "grad_norm": 22.194023114233552,
+      "learning_rate": 1.8220596619089573e-07,
+      "logits/chosen": 2.2478156089782715,
+      "logits/rejected": 3.0572941303253174,
+      "logps/chosen": -411.12042236328125,
+      "logps/rejected": -440.366455078125,
+      "loss": 0.5069,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.9174679517745972,
+      "rewards/margins": 0.7571024894714355,
+      "rewards/rejected": -1.6745704412460327,
+      "step": 300
+    },
+    {
+      "epoch": 0.6279434850863422,
+      "eval_logits/chosen": 3.1924495697021484,
+      "eval_logits/rejected": 3.7285730838775635,
+      "eval_logps/chosen": -351.63519287109375,
+      "eval_logps/rejected": -446.0467834472656,
+      "eval_loss": 0.5186473727226257,
+      "eval_rewards/accuracies": 0.77734375,
+      "eval_rewards/chosen": -0.918887734413147,
+      "eval_rewards/margins": 0.9378926157951355,
+      "eval_rewards/rejected": -1.8567802906036377,
+      "eval_runtime": 135.6583,
+      "eval_samples_per_second": 14.743,
+      "eval_steps_per_second": 0.236,
+      "step": 300
+    },
+    {
+      "epoch": 0.6488749345892203,
+      "grad_norm": 25.43913820730104,
+      "learning_rate": 1.647817538357072e-07,
+      "logits/chosen": 2.500638484954834,
+      "logits/rejected": 3.2447400093078613,
+      "logps/chosen": -402.08966064453125,
+      "logps/rejected": -451.0333557128906,
+      "loss": 0.5039,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.9885268211364746,
+      "rewards/margins": 1.0329763889312744,
+      "rewards/rejected": -2.02150297164917,
+      "step": 310
+    },
+    {
+      "epoch": 0.6698063840920984,
+      "grad_norm": 24.987168693662582,
+      "learning_rate": 1.478143389201113e-07,
+      "logits/chosen": 2.910473585128784,
+      "logits/rejected": 3.6681716442108154,
+      "logps/chosen": -362.282958984375,
+      "logps/rejected": -432.21893310546875,
+      "loss": 0.4876,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.0636372566223145,
+      "rewards/margins": 1.0137817859649658,
+      "rewards/rejected": -2.0774190425872803,
+      "step": 320
+    },
+    {
+      "epoch": 0.6907378335949764,
+      "grad_norm": 28.219288399554703,
+      "learning_rate": 1.3139467229135998e-07,
+      "logits/chosen": 2.3640151023864746,
+      "logits/rejected": 2.5420238971710205,
+      "logps/chosen": -365.45819091796875,
+      "logps/rejected": -448.38641357421875,
+      "loss": 0.5075,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.9718405604362488,
+      "rewards/margins": 0.8737540245056152,
+      "rewards/rejected": -1.8455946445465088,
+      "step": 330
+    },
+    {
+      "epoch": 0.7116692830978545,
+      "grad_norm": 34.63757657429248,
+      "learning_rate": 1.1561076868822755e-07,
+      "logits/chosen": 2.3741087913513184,
+      "logits/rejected": 2.8489933013916016,
+      "logps/chosen": -394.1705017089844,
+      "logps/rejected": -465.49383544921875,
+      "loss": 0.5049,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.054498314857483,
+      "rewards/margins": 0.9107035398483276,
+      "rewards/rejected": -1.965201735496521,
+      "step": 340
+    },
+    {
+      "epoch": 0.7326007326007326,
+      "grad_norm": 24.37249293073374,
+      "learning_rate": 1.0054723495346482e-07,
+      "logits/chosen": 2.3698134422302246,
+      "logits/rejected": 3.0672800540924072,
+      "logps/chosen": -363.47528076171875,
+      "logps/rejected": -426.842529296875,
+      "loss": 0.4744,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.0496411323547363,
+      "rewards/margins": 0.8752397298812866,
+      "rewards/rejected": -1.9248807430267334,
+      "step": 350
+    },
+    {
+      "epoch": 0.7535321821036107,
+      "grad_norm": 25.757971551121862,
+      "learning_rate": 8.628481651367875e-08,
+      "logits/chosen": 2.498418092727661,
+      "logits/rejected": 3.2870101928710938,
+      "logps/chosen": -409.0768127441406,
+      "logps/rejected": -469.11956787109375,
+      "loss": 0.5246,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.0417944192886353,
+      "rewards/margins": 1.0191967487335205,
+      "rewards/rejected": -2.060990810394287,
+      "step": 360
+    },
+    {
+      "epoch": 0.7744636316064888,
+      "grad_norm": 23.0161767515014,
+      "learning_rate": 7.289996455765748e-08,
+      "logits/chosen": 2.5688648223876953,
+      "logits/rejected": 3.2230935096740723,
+      "logps/chosen": -371.5119323730469,
+      "logps/rejected": -432.21209716796875,
+      "loss": 0.5184,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.0562775135040283,
+      "rewards/margins": 0.9286730885505676,
+      "rewards/rejected": -1.9849506616592407,
+      "step": 370
+    },
+    {
+      "epoch": 0.7953950811093669,
+      "grad_norm": 49.71616398607698,
+      "learning_rate": 6.046442623320145e-08,
+      "logits/chosen": 3.1454453468322754,
+      "logits/rejected": 3.4531302452087402,
+      "logps/chosen": -380.4229736328125,
+      "logps/rejected": -504.3771057128906,
+      "loss": 0.5011,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.325423002243042,
+      "rewards/margins": 1.0619542598724365,
+      "rewards/rejected": -2.3873772621154785,
+      "step": 380
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 26.297118450197193,
+      "learning_rate": 4.904486005914027e-08,
+      "logits/chosen": 2.315955638885498,
+      "logits/rejected": 2.94762921333313,
+      "logps/chosen": -456.85992431640625,
+      "logps/rejected": -503.12823486328125,
+      "loss": 0.4899,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.1912060976028442,
+      "rewards/margins": 0.8073137998580933,
+      "rewards/rejected": -1.9985198974609375,
+      "step": 390
+    },
+    {
+      "epoch": 0.837257980115123,
+      "grad_norm": 28.57839972535503,
+      "learning_rate": 3.8702478614051345e-08,
+      "logits/chosen": 2.724435567855835,
+      "logits/rejected": 3.432274580001831,
+      "logps/chosen": -371.2484436035156,
+      "logps/rejected": -445.4541931152344,
+      "loss": 0.5183,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -1.1717134714126587,
+      "rewards/margins": 0.889250636100769,
+      "rewards/rejected": -2.060964345932007,
+      "step": 400
+    },
+    {
+      "epoch": 0.837257980115123,
+      "eval_logits/chosen": 2.951892614364624,
+      "eval_logits/rejected": 3.4727354049682617,
+      "eval_logps/chosen": -363.58758544921875,
+      "eval_logps/rejected": -465.5700988769531,
+      "eval_loss": 0.5041975975036621,
+      "eval_rewards/accuracies": 0.77734375,
+      "eval_rewards/chosen": -1.038411259651184,
+      "eval_rewards/margins": 1.0136022567749023,
+      "eval_rewards/rejected": -2.052013397216797,
+      "eval_runtime": 134.6723,
+      "eval_samples_per_second": 14.851,
+      "eval_steps_per_second": 0.238,
+      "step": 400
+    },
+    {
+      "epoch": 0.858189429618001,
+      "grad_norm": 23.831407362545725,
+      "learning_rate": 2.9492720416985e-08,
+      "logits/chosen": 2.250394821166992,
+      "logits/rejected": 3.0254645347595215,
+      "logps/chosen": -411.3563537597656,
+      "logps/rejected": -476.86285400390625,
+      "loss": 0.5052,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -1.1620759963989258,
+      "rewards/margins": 0.949911892414093,
+      "rewards/rejected": -2.111988067626953,
+      "step": 410
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 27.663423223955505,
+      "learning_rate": 2.1464952759020856e-08,
+      "logits/chosen": 2.5075933933258057,
+      "logits/rejected": 3.0221657752990723,
+      "logps/chosen": -369.8209533691406,
+      "logps/rejected": -466.9547424316406,
+      "loss": 0.4991,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -1.132770299911499,
+      "rewards/margins": 0.9518559575080872,
+      "rewards/rejected": -2.0846264362335205,
+      "step": 420
+    },
+    {
+      "epoch": 0.9000523286237572,
+      "grad_norm": 32.43713821799361,
+      "learning_rate": 1.4662207078575684e-08,
+      "logits/chosen": 2.4172325134277344,
+      "logits/rejected": 3.0696935653686523,
+      "logps/chosen": -400.9945068359375,
+      "logps/rejected": -474.8321228027344,
+      "loss": 0.4789,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1254316568374634,
+      "rewards/margins": 0.9131272435188293,
+      "rewards/rejected": -2.0385589599609375,
+      "step": 430
+    },
+    {
+      "epoch": 0.9209837781266352,
+      "grad_norm": 25.627974700791466,
+      "learning_rate": 9.12094829893642e-09,
+      "logits/chosen": 2.092426061630249,
+      "logits/rejected": 2.797146797180176,
+      "logps/chosen": -367.8091735839844,
+      "logps/rejected": -422.43109130859375,
+      "loss": 0.4983,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0733999013900757,
+      "rewards/margins": 0.9040810465812683,
+      "rewards/rejected": -1.9774812459945679,
+      "step": 440
+    },
+    {
+      "epoch": 0.9419152276295133,
+      "grad_norm": 28.38366332873103,
+      "learning_rate": 4.8708793644441086e-09,
+      "logits/chosen": 2.500868320465088,
+      "logits/rejected": 3.0100467205047607,
+      "logps/chosen": -385.164306640625,
+      "logps/rejected": -472.8857421875,
+      "loss": 0.499,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.101036787033081,
+      "rewards/margins": 0.9818191528320312,
+      "rewards/rejected": -2.082855701446533,
+      "step": 450
+    },
+    {
+      "epoch": 0.9628466771323915,
+      "grad_norm": 25.01008394968339,
+      "learning_rate": 1.9347820230782295e-09,
+      "logits/chosen": 2.161432981491089,
+      "logits/rejected": 3.066352128982544,
+      "logps/chosen": -380.72161865234375,
+      "logps/rejected": -424.6839904785156,
+      "loss": 0.4969,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.0917384624481201,
+      "rewards/margins": 0.8798072934150696,
+      "rewards/rejected": -1.9715455770492554,
+      "step": 460
+    },
+    {
+      "epoch": 0.9837781266352695,
+      "grad_norm": 20.90504666692658,
+      "learning_rate": 3.2839470889836627e-10,
+      "logits/chosen": 2.2927355766296387,
+      "logits/rejected": 2.7883963584899902,
+      "logps/chosen": -401.99139404296875,
+      "logps/rejected": -455.39849853515625,
+      "loss": 0.4863,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.0055816173553467,
+      "rewards/margins": 0.8457299470901489,
+      "rewards/rejected": -1.851311445236206,
+      "step": 470
+    },
+    {
+      "epoch": 0.9984301412872841,
+      "step": 477,
+      "total_flos": 0.0,
+      "train_loss": 0.5498417743346976,
+      "train_runtime": 10726.7175,
+      "train_samples_per_second": 5.699,
+      "train_steps_per_second": 0.044
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 477,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}