Model save

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-dpo-full
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-7b-dpo-full
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5065
+- Rewards/chosen: -0.9786
+- Rewards/rejected: -1.9310
+- Rewards/accuracies: 0.7734
+- Rewards/margins: 0.9524
+- Logps/rejected: -455.7930
+- Logps/chosen: -360.4568
+- Logits/rejected: 0.2947
+- Logits/chosen: -0.6442
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5721        | 0.2092 | 100  | 0.5709          | -0.7941        | -1.3740          | 0.75               | 0.5798          | -400.0867      | -342.0089    | -1.1226         | -1.3180       |
+| 0.5453        | 0.4184 | 200  | 0.5234          | -1.0595        | -1.8701          | 0.7773             | 0.8105          | -449.6958      | -368.5487    | 0.0691          | -0.6851       |
+| 0.4933        | 0.6276 | 300  | 0.5102          | -1.0953        | -2.0092          | 0.7695             | 0.9139          | -463.6079      | -372.1221    | 0.3510          | -0.4567       |
+| 0.4979        | 0.8368 | 400  | 0.5065          | -0.9786        | -1.9310          | 0.7734             | 0.9524          | -455.7930      | -360.4568    | 0.2947          | -0.6442       |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.5389037092360492,
+    "train_runtime": 7287.4677,
+    "train_samples": 61134,
+    "train_samples_per_second": 8.389,
+    "train_steps_per_second": 0.066
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e2f75a9dcdeb1e41e5ab93008b61f13e5922bf442844592d9fd74e4affc772
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b97aa9a38fdf33fe9b50905a5300edc31712f0935e8be39a7f8bf768d659c2
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e8d45692a1449552f6e80380bf680b5fa08556336a004db80b58ea1fba44ff
+size 4540516344

model.safetensors.index.json

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

runs/May16_15-36-14_n136-083-012/events.out.tfevents.1715845553.n136-083-012.3293363.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:517b7405f571a51ec446587cf0e86e32b9f35159fa12b32c6dbea53d7c6f3870
-size 35841
+oid sha256:337cbcfa0ce7e4643e3718db08bd723449212b2c806d09a262ff4368bfce6359
+size 41011

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.5389037092360492,
+    "train_runtime": 7287.4677,
+    "train_samples": 61134,
+    "train_samples_per_second": 8.389,
+    "train_steps_per_second": 0.066
+}

trainer_state.json

@@ -0,0 +1,814 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 478,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0020920502092050207,
+      "grad_norm": 9.114838741938676,
+      "learning_rate": 1.0416666666666666e-08,
+      "logits/chosen": -2.7657570838928223,
+      "logits/rejected": -2.7161638736724854,
+      "logps/chosen": -269.82177734375,
+      "logps/rejected": -360.38824462890625,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.02092050209205021,
+      "grad_norm": 9.148919161158942,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -2.5925657749176025,
+      "logits/rejected": -2.5628323554992676,
+      "logps/chosen": -264.7928771972656,
+      "logps/rejected": -251.55447387695312,
+      "loss": 0.693,
+      "rewards/accuracies": 0.4305555522441864,
+      "rewards/chosen": -6.324940477497876e-05,
+      "rewards/margins": 7.682020805077627e-05,
+      "rewards/rejected": -0.0001400695473421365,
+      "step": 10
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "grad_norm": 8.40346707523924,
+      "learning_rate": 2.0833333333333333e-07,
+      "logits/chosen": -2.6535439491271973,
+      "logits/rejected": -2.6055901050567627,
+      "logps/chosen": -281.4295654296875,
+      "logps/rejected": -296.7832946777344,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.5249999761581421,
+      "rewards/chosen": 0.000975612667389214,
+      "rewards/margins": 0.0008926031878218055,
+      "rewards/rejected": 8.300942135974765e-05,
+      "step": 20
+    },
+    {
+      "epoch": 0.06276150627615062,
+      "grad_norm": 8.289266699202459,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -2.6645305156707764,
+      "logits/rejected": -2.5921378135681152,
+      "logps/chosen": -299.45953369140625,
+      "logps/rejected": -263.7018737792969,
+      "loss": 0.6884,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 0.011769616976380348,
+      "rewards/margins": 0.00957556813955307,
+      "rewards/rejected": 0.002194049535319209,
+      "step": 30
+    },
+    {
+      "epoch": 0.08368200836820083,
+      "grad_norm": 8.184157355462025,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -2.5577497482299805,
+      "logits/rejected": -2.522876501083374,
+      "logps/chosen": -263.11431884765625,
+      "logps/rejected": -245.15869140625,
+      "loss": 0.6773,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.04037148505449295,
+      "rewards/margins": 0.04829186201095581,
+      "rewards/rejected": -0.007920385338366032,
+      "step": 40
+    },
+    {
+      "epoch": 0.10460251046025104,
+      "grad_norm": 8.435209329134775,
+      "learning_rate": 4.999733114418725e-07,
+      "logits/chosen": -2.4979910850524902,
+      "logits/rejected": -2.4582855701446533,
+      "logps/chosen": -279.7125549316406,
+      "logps/rejected": -297.5962829589844,
+      "loss": 0.6612,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.0005922674899920821,
+      "rewards/margins": 0.0489339753985405,
+      "rewards/rejected": -0.04834171012043953,
+      "step": 50
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "grad_norm": 11.259979497893776,
+      "learning_rate": 4.990398100856366e-07,
+      "logits/chosen": -2.5113587379455566,
+      "logits/rejected": -2.4398372173309326,
+      "logps/chosen": -274.03460693359375,
+      "logps/rejected": -313.31854248046875,
+      "loss": 0.6386,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": -0.024031374603509903,
+      "rewards/margins": 0.12788036465644836,
+      "rewards/rejected": -0.15191176533699036,
+      "step": 60
+    },
+    {
+      "epoch": 0.14644351464435146,
+      "grad_norm": 10.74158006735161,
+      "learning_rate": 4.967775735898179e-07,
+      "logits/chosen": -2.3557136058807373,
+      "logits/rejected": -2.35380220413208,
+      "logps/chosen": -270.8974914550781,
+      "logps/rejected": -283.5448303222656,
+      "loss": 0.6154,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -0.05267774313688278,
+      "rewards/margins": 0.21590645611286163,
+      "rewards/rejected": -0.2685841917991638,
+      "step": 70
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 18.36717279276638,
+      "learning_rate": 4.931986719649298e-07,
+      "logits/chosen": -2.55155611038208,
+      "logits/rejected": -2.4677367210388184,
+      "logps/chosen": -335.8424377441406,
+      "logps/rejected": -304.39422607421875,
+      "loss": 0.6025,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.13085874915122986,
+      "rewards/margins": 0.27254563570022583,
+      "rewards/rejected": -0.4034043848514557,
+      "step": 80
+    },
+    {
+      "epoch": 0.18828451882845187,
+      "grad_norm": 19.750489526157647,
+      "learning_rate": 4.883222001996351e-07,
+      "logits/chosen": -2.1238503456115723,
+      "logits/rejected": -2.062669515609741,
+      "logps/chosen": -316.478759765625,
+      "logps/rejected": -356.72064208984375,
+      "loss": 0.5726,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.5738530158996582,
+      "rewards/margins": 0.46993812918663025,
+      "rewards/rejected": -1.0437911748886108,
+      "step": 90
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 19.534863791068346,
+      "learning_rate": 4.821741763807186e-07,
+      "logits/chosen": -1.748064398765564,
+      "logits/rejected": -1.5715205669403076,
+      "logps/chosen": -317.5589904785156,
+      "logps/rejected": -366.8465881347656,
+      "loss": 0.5721,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.5714582204818726,
+      "rewards/margins": 0.5261567234992981,
+      "rewards/rejected": -1.0976150035858154,
+      "step": 100
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "eval_logits/chosen": -1.3179829120635986,
+      "eval_logits/rejected": -1.1225839853286743,
+      "eval_logps/chosen": -342.0088806152344,
+      "eval_logps/rejected": -400.0867004394531,
+      "eval_loss": 0.5708911418914795,
+      "eval_rewards/accuracies": 0.75,
+      "eval_rewards/chosen": -0.794143557548523,
+      "eval_rewards/margins": 0.579823911190033,
+      "eval_rewards/rejected": -1.3739675283432007,
+      "eval_runtime": 93.6405,
+      "eval_samples_per_second": 21.358,
+      "eval_steps_per_second": 0.342,
+      "step": 100
+    },
+    {
+      "epoch": 0.2301255230125523,
+      "grad_norm": 16.836485949069047,
+      "learning_rate": 4.747874028753375e-07,
+      "logits/chosen": -1.653177261352539,
+      "logits/rejected": -1.2800805568695068,
+      "logps/chosen": -376.3698425292969,
+      "logps/rejected": -382.333740234375,
+      "loss": 0.5707,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.718134880065918,
+      "rewards/margins": 0.5270050168037415,
+      "rewards/rejected": -1.2451398372650146,
+      "step": 110
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 19.509469868973294,
+      "learning_rate": 4.662012913161997e-07,
+      "logits/chosen": -1.804979920387268,
+      "logits/rejected": -1.5728490352630615,
+      "logps/chosen": -337.7046813964844,
+      "logps/rejected": -368.3199462890625,
+      "loss": 0.5551,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.5655803084373474,
+      "rewards/margins": 0.5188466310501099,
+      "rewards/rejected": -1.084426999092102,
+      "step": 120
+    },
+    {
+      "epoch": 0.2719665271966527,
+      "grad_norm": 19.27903074764292,
+      "learning_rate": 4.5646165232345103e-07,
+      "logits/chosen": -0.6531444787979126,
+      "logits/rejected": -0.3025096356868744,
+      "logps/chosen": -387.9170227050781,
+      "logps/rejected": -435.4076232910156,
+      "loss": 0.5431,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.0594689846038818,
+      "rewards/margins": 0.6101099252700806,
+      "rewards/rejected": -1.6695789098739624,
+      "step": 130
+    },
+    {
+      "epoch": 0.2928870292887029,
+      "grad_norm": 16.354855198007613,
+      "learning_rate": 4.456204510851956e-07,
+      "logits/chosen": -1.4554462432861328,
+      "logits/rejected": -1.1778004169464111,
+      "logps/chosen": -390.60955810546875,
+      "logps/rejected": -440.247802734375,
+      "loss": 0.54,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.7465543150901794,
+      "rewards/margins": 0.6489186882972717,
+      "rewards/rejected": -1.3954730033874512,
+      "step": 140
+    },
+    {
+      "epoch": 0.3138075313807531,
+      "grad_norm": 24.226359563566024,
+      "learning_rate": 4.337355301007335e-07,
+      "logits/chosen": -1.3749992847442627,
+      "logits/rejected": -0.969765841960907,
+      "logps/chosen": -358.49078369140625,
+      "logps/rejected": -404.18414306640625,
+      "loss": 0.5431,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.7523535490036011,
+      "rewards/margins": 0.5271070599555969,
+      "rewards/rejected": -1.2794606685638428,
+      "step": 150
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 21.61030528838648,
+      "learning_rate": 4.2087030056579986e-07,
+      "logits/chosen": -0.8662149310112,
+      "logits/rejected": -0.03768510743975639,
+      "logps/chosen": -348.19110107421875,
+      "logps/rejected": -414.1924743652344,
+      "loss": 0.5339,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.751144528388977,
+      "rewards/margins": 0.816437840461731,
+      "rewards/rejected": -1.567582368850708,
+      "step": 160
+    },
+    {
+      "epoch": 0.35564853556485354,
+      "grad_norm": 25.081015553348266,
+      "learning_rate": 4.070934040463998e-07,
+      "logits/chosen": -0.5068038702011108,
+      "logits/rejected": 0.02004914917051792,
+      "logps/chosen": -347.1032409667969,
+      "logps/rejected": -390.4936218261719,
+      "loss": 0.5373,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.9777852892875671,
+      "rewards/margins": 0.6159799098968506,
+      "rewards/rejected": -1.5937652587890625,
+      "step": 170
+    },
+    {
+      "epoch": 0.37656903765690375,
+      "grad_norm": 22.866857199887985,
+      "learning_rate": 3.9247834624635404e-07,
+      "logits/chosen": -0.23705987632274628,
+      "logits/rejected": 0.5616781115531921,
+      "logps/chosen": -346.0610046386719,
+      "logps/rejected": -389.42266845703125,
+      "loss": 0.504,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.8973515629768372,
+      "rewards/margins": 0.7208992838859558,
+      "rewards/rejected": -1.618250846862793,
+      "step": 180
+    },
+    {
+      "epoch": 0.39748953974895396,
+      "grad_norm": 24.94627804784251,
+      "learning_rate": 3.7710310482256523e-07,
+      "logits/chosen": -0.8781476020812988,
+      "logits/rejected": -0.1542932391166687,
+      "logps/chosen": -354.30511474609375,
+      "logps/rejected": -408.465087890625,
+      "loss": 0.5198,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.8304754495620728,
+      "rewards/margins": 0.656559944152832,
+      "rewards/rejected": -1.4870353937149048,
+      "step": 190
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 54.582944800282775,
+      "learning_rate": 3.610497133404795e-07,
+      "logits/chosen": -0.2953304350376129,
+      "logits/rejected": 0.3064122796058655,
+      "logps/chosen": -377.56585693359375,
+      "logps/rejected": -445.3349609375,
+      "loss": 0.5453,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -1.1766728162765503,
+      "rewards/margins": 0.7559624910354614,
+      "rewards/rejected": -1.9326353073120117,
+      "step": 200
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "eval_logits/chosen": -0.6850857138633728,
+      "eval_logits/rejected": 0.06908559799194336,
+      "eval_logps/chosen": -368.5487365722656,
+      "eval_logps/rejected": -449.69580078125,
+      "eval_loss": 0.5234317779541016,
+      "eval_rewards/accuracies": 0.77734375,
+      "eval_rewards/chosen": -1.0595417022705078,
+      "eval_rewards/margins": 0.8105169534683228,
+      "eval_rewards/rejected": -1.8700587749481201,
+      "eval_runtime": 93.2417,
+      "eval_samples_per_second": 21.45,
+      "eval_steps_per_second": 0.343,
+      "step": 200
+    },
+    {
+      "epoch": 0.4393305439330544,
+      "grad_norm": 22.215260502674298,
+      "learning_rate": 3.4440382358952115e-07,
+      "logits/chosen": -0.8639524579048157,
+      "logits/rejected": 0.09512700885534286,
+      "logps/chosen": -388.6444396972656,
+      "logps/rejected": -420.42059326171875,
+      "loss": 0.5352,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.9897388219833374,
+      "rewards/margins": 0.7016456723213196,
+      "rewards/rejected": -1.6913845539093018,
+      "step": 210
+    },
+    {
+      "epoch": 0.4602510460251046,
+      "grad_norm": 28.81162780553365,
+      "learning_rate": 3.272542485937368e-07,
+      "logits/chosen": -0.590522289276123,
+      "logits/rejected": 0.5216765999794006,
+      "logps/chosen": -356.6697998046875,
+      "logps/rejected": -414.6576232910156,
+      "loss": 0.5257,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.9125692248344421,
+      "rewards/margins": 0.7771139144897461,
+      "rewards/rejected": -1.6896833181381226,
+      "step": 220
+    },
+    {
+      "epoch": 0.4811715481171548,
+      "grad_norm": 22.014587897898174,
+      "learning_rate": 3.096924887558854e-07,
+      "logits/chosen": -0.23531527817249298,
+      "logits/rejected": 0.6261798739433289,
+      "logps/chosen": -356.0992126464844,
+      "logps/rejected": -447.2344665527344,
+      "loss": 0.5345,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.0719140768051147,
+      "rewards/margins": 0.9232422709465027,
+      "rewards/rejected": -1.9951562881469727,
+      "step": 230
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 22.011427681667726,
+      "learning_rate": 2.9181224366319943e-07,
+      "logits/chosen": -0.6749089360237122,
+      "logits/rejected": 0.12929710745811462,
+      "logps/chosen": -358.3074645996094,
+      "logps/rejected": -418.3113708496094,
+      "loss": 0.4973,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -0.9459273219108582,
+      "rewards/margins": 0.7464773058891296,
+      "rewards/rejected": -1.6924045085906982,
+      "step": 240
+    },
+    {
+      "epoch": 0.5230125523012552,
+      "grad_norm": 26.657610582356075,
+      "learning_rate": 2.7370891215954565e-07,
+      "logits/chosen": -0.5687319040298462,
+      "logits/rejected": 0.5906481742858887,
+      "logps/chosen": -382.4239196777344,
+      "logps/rejected": -431.86541748046875,
+      "loss": 0.5024,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.8423226475715637,
+      "rewards/margins": 0.8808477520942688,
+      "rewards/rejected": -1.723170518875122,
+      "step": 250
+    },
+    {
+      "epoch": 0.5439330543933054,
+      "grad_norm": 30.03729314534647,
+      "learning_rate": 2.55479083351317e-07,
+      "logits/chosen": -0.01633582077920437,
+      "logits/rejected": 1.0996766090393066,
+      "logps/chosen": -409.0030822753906,
+      "logps/rejected": -453.35797119140625,
+      "loss": 0.5088,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.14716374874115,
+      "rewards/margins": 0.8472634553909302,
+      "rewards/rejected": -1.9944270849227905,
+      "step": 260
+    },
+    {
+      "epoch": 0.5648535564853556,
+      "grad_norm": 25.404389397429885,
+      "learning_rate": 2.3722002126275822e-07,
+      "logits/chosen": 0.10315756499767303,
+      "logits/rejected": 0.8474380373954773,
+      "logps/chosen": -402.7615661621094,
+      "logps/rejected": -453.3907165527344,
+      "loss": 0.5181,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.2571824789047241,
+      "rewards/margins": 0.7002416849136353,
+      "rewards/rejected": -1.9574241638183594,
+      "step": 270
+    },
+    {
+      "epoch": 0.5857740585774058,
+      "grad_norm": 24.907684608681677,
+      "learning_rate": 2.19029145890313e-07,
+      "logits/chosen": -0.4998618960380554,
+      "logits/rejected": 0.5520098805427551,
+      "logps/chosen": -361.79339599609375,
+      "logps/rejected": -421.1419982910156,
+      "loss": 0.5279,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -1.001235842704773,
+      "rewards/margins": 0.7880947589874268,
+      "rewards/rejected": -1.7893307209014893,
+      "step": 280
+    },
+    {
+      "epoch": 0.606694560669456,
+      "grad_norm": 23.055490421391816,
+      "learning_rate": 2.0100351342479216e-07,
+      "logits/chosen": -0.9633615612983704,
+      "logits/rejected": 0.04775930196046829,
+      "logps/chosen": -350.3211364746094,
+      "logps/rejected": -417.6044921875,
+      "loss": 0.514,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.9923901557922363,
+      "rewards/margins": 0.7642750144004822,
+      "rewards/rejected": -1.7566652297973633,
+      "step": 290
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 29.729151533876507,
+      "learning_rate": 1.8323929841460178e-07,
+      "logits/chosen": -0.7032476663589478,
+      "logits/rejected": 0.3550058901309967,
+      "logps/chosen": -416.74896240234375,
+      "logps/rejected": -452.7919006347656,
+      "loss": 0.4933,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -1.1573503017425537,
+      "rewards/margins": 0.7699189782142639,
+      "rewards/rejected": -1.9272693395614624,
+      "step": 300
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "eval_logits/chosen": -0.4567390978336334,
+      "eval_logits/rejected": 0.3510359227657318,
+      "eval_logps/chosen": -372.1221008300781,
+      "eval_logps/rejected": -463.6078796386719,
+      "eval_loss": 0.5101574063301086,
+      "eval_rewards/accuracies": 0.76953125,
+      "eval_rewards/chosen": -1.09527587890625,
+      "eval_rewards/margins": 0.9139033555984497,
+      "eval_rewards/rejected": -2.0091793537139893,
+      "eval_runtime": 93.2411,
+      "eval_samples_per_second": 21.45,
+      "eval_steps_per_second": 0.343,
+      "step": 300
+    },
+    {
+      "epoch": 0.6485355648535565,
+      "grad_norm": 25.3862275508519,
+      "learning_rate": 1.6583128063291573e-07,
+      "logits/chosen": -0.5110741257667542,
+      "logits/rejected": 0.2962663173675537,
+      "logps/chosen": -411.4129333496094,
+      "logps/rejected": -451.06915283203125,
+      "loss": 0.4869,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.1609933376312256,
+      "rewards/margins": 0.7645314931869507,
+      "rewards/rejected": -1.9255249500274658,
+      "step": 310
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 31.877509645415845,
+      "learning_rate": 1.488723393865766e-07,
+      "logits/chosen": -0.42931467294692993,
+      "logits/rejected": 0.4852021336555481,
+      "logps/chosen": -406.82098388671875,
+      "logps/rejected": -437.549072265625,
+      "loss": 0.4844,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.131407618522644,
+      "rewards/margins": 0.7958317995071411,
+      "rewards/rejected": -1.9272394180297852,
+      "step": 320
+    },
+    {
+      "epoch": 0.6903765690376569,
+      "grad_norm": 31.651952816649054,
+      "learning_rate": 1.3245295796480788e-07,
+      "logits/chosen": -0.7463265061378479,
+      "logits/rejected": 0.1753389537334442,
+      "logps/chosen": -364.3424377441406,
+      "logps/rejected": -436.80145263671875,
+      "loss": 0.4953,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -1.0208923816680908,
+      "rewards/margins": 0.7519049644470215,
+      "rewards/rejected": -1.7727975845336914,
+      "step": 330
+    },
+    {
+      "epoch": 0.7112970711297071,
+      "grad_norm": 36.415357529261385,
+      "learning_rate": 1.1666074087171627e-07,
+      "logits/chosen": -0.632677435874939,
+      "logits/rejected": 0.38786324858665466,
+      "logps/chosen": -379.0039367675781,
+      "logps/rejected": -474.87353515625,
+      "loss": 0.5037,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -0.889354407787323,
+      "rewards/margins": 1.0584837198257446,
+      "rewards/rejected": -1.9478381872177124,
+      "step": 340
+    },
+    {
+      "epoch": 0.7322175732217573,
+      "grad_norm": 24.247963237747875,
+      "learning_rate": 1.0157994641835734e-07,
+      "logits/chosen": -0.3200559914112091,
+      "logits/rejected": 0.48934563994407654,
+      "logps/chosen": -363.71099853515625,
+      "logps/rejected": -433.1835021972656,
+      "loss": 0.4749,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.0547664165496826,
+      "rewards/margins": 0.8703587651252747,
+      "rewards/rejected": -1.9251251220703125,
+      "step": 350
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "grad_norm": 23.717563683514285,
+      "learning_rate": 8.729103716819111e-08,
+      "logits/chosen": -0.5418771505355835,
+      "logits/rejected": 0.7592712044715881,
+      "logps/chosen": -418.52642822265625,
+      "logps/rejected": -470.0746154785156,
+      "loss": 0.511,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.1582874059677124,
+      "rewards/margins": 0.9300657510757446,
+      "rewards/rejected": -2.088352918624878,
+      "step": 360
+    },
+    {
+      "epoch": 0.7740585774058577,
+      "grad_norm": 24.001576803906307,
+      "learning_rate": 7.387025063449081e-08,
+      "logits/chosen": -0.2922624349594116,
+      "logits/rejected": 0.5890587568283081,
+      "logps/chosen": -402.0556945800781,
+      "logps/rejected": -438.61114501953125,
+      "loss": 0.5059,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.2673383951187134,
+      "rewards/margins": 0.7362791299819946,
+      "rewards/rejected": -2.003617763519287,
+      "step": 370
+    },
+    {
+      "epoch": 0.7949790794979079,
+      "grad_norm": 25.793595229742976,
+      "learning_rate": 6.138919252022435e-08,
+      "logits/chosen": -0.2611263394355774,
+      "logits/rejected": 0.6307548880577087,
+      "logps/chosen": -374.634033203125,
+      "logps/rejected": -485.6241760253906,
+      "loss": 0.5023,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.351632833480835,
+      "rewards/margins": 0.9176739454269409,
+      "rewards/rejected": -2.2693068981170654,
+      "step": 380
+    },
+    {
+      "epoch": 0.8158995815899581,
+      "grad_norm": 25.772278577526524,
+      "learning_rate": 4.991445467064689e-08,
+      "logits/chosen": -0.6276550889015198,
+      "logits/rejected": 0.06915655732154846,
+      "logps/chosen": -414.494873046875,
+      "logps/rejected": -474.9319763183594,
+      "loss": 0.4918,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -1.0889649391174316,
+      "rewards/margins": 0.8210123181343079,
+      "rewards/rejected": -1.9099773168563843,
+      "step": 390
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 26.774828562806604,
+      "learning_rate": 3.9507259776993954e-08,
+      "logits/chosen": -0.5621662735939026,
+      "logits/rejected": 0.6409434080123901,
+      "logps/chosen": -381.43353271484375,
+      "logps/rejected": -469.0619201660156,
+      "loss": 0.4979,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.1089556217193604,
+      "rewards/margins": 0.9117926359176636,
+      "rewards/rejected": -2.0207479000091553,
+      "step": 400
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "eval_logits/chosen": -0.6441599726676941,
+      "eval_logits/rejected": 0.29468241333961487,
+      "eval_logps/chosen": -360.4567565917969,
+      "eval_logps/rejected": -455.79302978515625,
+      "eval_loss": 0.5064861178398132,
+      "eval_rewards/accuracies": 0.7734375,
+      "eval_rewards/chosen": -0.9786220788955688,
+      "eval_rewards/margins": 0.9524084329605103,
+      "eval_rewards/rejected": -1.9310303926467896,
+      "eval_runtime": 93.2531,
+      "eval_samples_per_second": 21.447,
+      "eval_steps_per_second": 0.343,
+      "step": 400
+    },
+    {
+      "epoch": 0.8577405857740585,
+      "grad_norm": 26.337679734960755,
+      "learning_rate": 3.022313472693447e-08,
+      "logits/chosen": -0.6503273248672485,
+      "logits/rejected": 0.5346375107765198,
+      "logps/chosen": -402.32269287109375,
+      "logps/rejected": -462.08587646484375,
+      "loss": 0.5074,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.0340006351470947,
+      "rewards/margins": 0.8984886407852173,
+      "rewards/rejected": -1.9324891567230225,
+      "step": 410
+    },
+    {
+      "epoch": 0.8786610878661087,
+      "grad_norm": 25.989820003983546,
+      "learning_rate": 2.2111614344599684e-08,
+      "logits/chosen": -0.6875001192092896,
+      "logits/rejected": 0.2544765770435333,
+      "logps/chosen": -401.7547302246094,
+      "logps/rejected": -460.9256896972656,
+      "loss": 0.4944,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.046701192855835,
+      "rewards/margins": 0.8177343606948853,
+      "rewards/rejected": -1.8644355535507202,
+      "step": 420
+    },
+    {
+      "epoch": 0.899581589958159,
+      "grad_norm": 25.092036623232836,
+      "learning_rate": 1.521597710086439e-08,
+      "logits/chosen": -0.3008420467376709,
+      "logits/rejected": 0.7480442523956299,
+      "logps/chosen": -395.1468811035156,
+      "logps/rejected": -463.54339599609375,
+      "loss": 0.4748,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.1613723039627075,
+      "rewards/margins": 0.8963526487350464,
+      "rewards/rejected": -2.057724714279175,
+      "step": 430
+    },
+    {
+      "epoch": 0.9205020920502092,
+      "grad_norm": 29.09669611679921,
+      "learning_rate": 9.57301420397924e-09,
+      "logits/chosen": -0.6145204305648804,
+      "logits/rejected": 0.5261214971542358,
+      "logps/chosen": -387.2932434082031,
+      "logps/rejected": -455.5185546875,
+      "loss": 0.4984,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.0299204587936401,
+      "rewards/margins": 0.8344703912734985,
+      "rewards/rejected": -1.8643907308578491,
+      "step": 440
+    },
+    {
+      "epoch": 0.9414225941422594,
+      "grad_norm": 24.430323070169926,
+      "learning_rate": 5.212833302556258e-09,
+      "logits/chosen": -0.5034903287887573,
+      "logits/rejected": 0.39524441957473755,
+      "logps/chosen": -405.39599609375,
+      "logps/rejected": -503.2265625,
+      "loss": 0.4952,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -1.1170603036880493,
+      "rewards/margins": 0.8440200090408325,
+      "rewards/rejected": -1.9610801935195923,
+      "step": 450
+    },
+    {
+      "epoch": 0.9623430962343096,
+      "grad_norm": 29.61034065147898,
+      "learning_rate": 2.158697848236607e-09,
+      "logits/chosen": -0.4550473690032959,
+      "logits/rejected": 0.6017940640449524,
+      "logps/chosen": -377.21063232421875,
+      "logps/rejected": -430.52008056640625,
+      "loss": 0.4979,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -1.0525791645050049,
+      "rewards/margins": 0.8260202407836914,
+      "rewards/rejected": -1.8785991668701172,
+      "step": 460
+    },
+    {
+      "epoch": 0.9832635983263598,
+      "grad_norm": 25.666198685002744,
+      "learning_rate": 4.269029751107489e-10,
+      "logits/chosen": -0.5700952410697937,
+      "logits/rejected": 0.6865329742431641,
+      "logps/chosen": -384.0159912109375,
+      "logps/rejected": -475.2630310058594,
+      "loss": 0.4878,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.0533204078674316,
+      "rewards/margins": 0.8755053281784058,
+      "rewards/rejected": -1.9288257360458374,
+      "step": 470
+    },
+    {
+      "epoch": 1.0,
+      "step": 478,
+      "total_flos": 0.0,
+      "train_loss": 0.5389037092360492,
+      "train_runtime": 7287.4677,
+      "train_samples_per_second": 8.389,
+      "train_steps_per_second": 0.066
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 478,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}