Model save

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-dpo-full
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-7b-dpo-full
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8483
+- Rewards/chosen: 0.7019
+- Rewards/rejected: -1.3716
+- Rewards/accuracies: 0.6786
+- Rewards/margins: 2.0734
+- Logps/rejected: -263.1501
+- Logps/chosen: -283.4079
+- Logits/rejected: -2.6313
+- Logits/chosen: -2.6617
+
+## 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: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.9481        | 0.42  | 200  | 0.9533          | -0.6644        | -2.6641          | 0.7163             | 1.9997          | -264.4427      | -284.7741    | -2.6754         | -2.7043       |
+| 1.0499        | 0.84  | 400  | 0.8542          | 0.5163         | -1.5982          | 0.6766             | 2.1145          | -263.3767      | -283.5935    | -2.6278         | -2.6586       |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.6617116928100586,
+    "eval_logits/rejected": -2.631270170211792,
+    "eval_logps/chosen": -283.40789794921875,
+    "eval_logps/rejected": -263.1501159667969,
+    "eval_loss": 0.8482561111450195,
+    "eval_rewards/accuracies": 0.6785714030265808,
+    "eval_rewards/chosen": 0.7018745541572571,
+    "eval_rewards/margins": 2.07344651222229,
+    "eval_rewards/rejected": -1.3715722560882568,
+    "eval_runtime": 235.9971,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 8.475,
+    "eval_steps_per_second": 0.267,
+    "train_loss": 0.9276265908087324,
+    "train_runtime": 18165.5867,
+    "train_samples": 61135,
+    "train_samples_per_second": 3.365,
+    "train_steps_per_second": 0.026
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.6617116928100586,
+    "eval_logits/rejected": -2.631270170211792,
+    "eval_logps/chosen": -283.40789794921875,
+    "eval_logps/rejected": -263.1501159667969,
+    "eval_loss": 0.8482561111450195,
+    "eval_rewards/accuracies": 0.6785714030265808,
+    "eval_rewards/chosen": 0.7018745541572571,
+    "eval_rewards/margins": 2.07344651222229,
+    "eval_rewards/rejected": -1.3715722560882568,
+    "eval_runtime": 235.9971,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 8.475,
+    "eval_steps_per_second": 0.267
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3713d3a63f8855480214ffeac2abf013a70c70d999108a19486c2a9fc116748
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617db246bd6bf63b8bf154ab2ccb1bbd7ada255d2149c6227cd24a330d393695
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554b91cfd8cc824feb0e60d5567248dd051b97e1d0d7d70b0fee22f08b840309
+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/Jun04_06-55-20_temp1a22200000C/events.out.tfevents.1717484155.temp1a22200000C.489069.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081da16a7ec84e37bc8f025320c9aba85bb3d07359cf5f8158c2af6db67c38a1
+size 4481

runs/Jun04_06-57-18_temp1a22200000C/events.out.tfevents.1717484289.temp1a22200000C.489885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2b9642eb0dd5f02a5dcee262cab8313fb00b7a4dcbe70d1db7321999bca2be
+size 36604

runs/Jun04_06-57-18_temp1a22200000C/events.out.tfevents.1717502690.temp1a22200000C.489885.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcfdb6081abfceaee3444d9fedf280e10d98f1b6c9a64b9eadfeb5d82523b8c6
+size 828

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9276265908087324,
+    "train_runtime": 18165.5867,
+    "train_samples": 61135,
+    "train_samples_per_second": 3.365,
+    "train_steps_per_second": 0.026
+}

trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984301412872841,
+  "eval_steps": 200,
+  "global_step": 477,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0416666666666666e-08,
+      "logits/chosen": -2.7851884365081787,
+      "logits/rejected": -2.649298906326294,
+      "logps/chosen": -296.01092529296875,
+      "logps/rejected": -290.09039306640625,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -2.648496389389038,
+      "logits/rejected": -2.668022394180298,
+      "logps/chosen": -278.4987487792969,
+      "logps/rejected": -242.15708923339844,
+      "loss": 0.7226,
+      "rewards/accuracies": 0.4861111044883728,
+      "rewards/chosen": 0.06170377507805824,
+      "rewards/margins": 0.054149795323610306,
+      "rewards/rejected": 0.007553977891802788,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.0833333333333333e-07,
+      "logits/chosen": -2.6808462142944336,
+      "logits/rejected": -2.656245470046997,
+      "logps/chosen": -276.23272705078125,
+      "logps/rejected": -246.00448608398438,
+      "loss": 0.6864,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.09794271737337112,
+      "rewards/margins": 0.13353291153907776,
+      "rewards/rejected": -0.03559018298983574,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -2.6753792762756348,
+      "logits/rejected": -2.658241033554077,
+      "logps/chosen": -291.89227294921875,
+      "logps/rejected": -274.1100769042969,
+      "loss": 0.657,
+      "rewards/accuracies": 0.65625,
+      "rewards/chosen": 0.4894474148750305,
+      "rewards/margins": 0.5969166159629822,
+      "rewards/rejected": -0.10746921598911285,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -2.6500256061553955,
+      "logits/rejected": -2.640502452850342,
+      "logps/chosen": -306.4776916503906,
+      "logps/rejected": -277.1504821777344,
+      "loss": 0.6103,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": 1.0548440217971802,
+      "rewards/margins": 1.0432922840118408,
+      "rewards/rejected": 0.011551743373274803,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.999731868769026e-07,
+      "logits/chosen": -2.6383259296417236,
+      "logits/rejected": -2.6259989738464355,
+      "logps/chosen": -298.2965087890625,
+      "logps/rejected": -280.02117919921875,
+      "loss": 0.6394,
+      "rewards/accuracies": 0.6968749761581421,
+      "rewards/chosen": 0.34443342685699463,
+      "rewards/margins": 1.087842583656311,
+      "rewards/rejected": -0.7434090375900269,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.990353313429303e-07,
+      "logits/chosen": -2.6224470138549805,
+      "logits/rejected": -2.572944402694702,
+      "logps/chosen": -282.615966796875,
+      "logps/rejected": -236.1990966796875,
+      "loss": 0.8549,
+      "rewards/accuracies": 0.684374988079071,
+      "rewards/chosen": 0.3339448571205139,
+      "rewards/margins": 1.3397847414016724,
+      "rewards/rejected": -1.0058400630950928,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.967625656594781e-07,
+      "logits/chosen": -2.6648612022399902,
+      "logits/rejected": -2.6511025428771973,
+      "logps/chosen": -278.946044921875,
+      "logps/rejected": -247.79544067382812,
+      "loss": 0.6758,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 1.0940700769424438,
+      "rewards/margins": 1.4048646688461304,
+      "rewards/rejected": -0.3107944428920746,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.93167072587771e-07,
+      "logits/chosen": -2.652858257293701,
+      "logits/rejected": -2.648376703262329,
+      "logps/chosen": -286.8718566894531,
+      "logps/rejected": -288.487548828125,
+      "loss": 1.0973,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.4459499418735504,
+      "rewards/margins": 0.44234198331832886,
+      "rewards/rejected": -0.8882920145988464,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.882681251368548e-07,
+      "logits/chosen": -2.6302177906036377,
+      "logits/rejected": -2.6423885822296143,
+      "logps/chosen": -260.6453857421875,
+      "logps/rejected": -240.8030548095703,
+      "loss": 0.7506,
+      "rewards/accuracies": 0.690625011920929,
+      "rewards/chosen": 0.48692113161087036,
+      "rewards/margins": 1.6797454357147217,
+      "rewards/rejected": -1.192824125289917,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.820919832540181e-07,
+      "logits/chosen": -2.7023916244506836,
+      "logits/rejected": -2.6528306007385254,
+      "logps/chosen": -280.9873046875,
+      "logps/rejected": -265.68017578125,
+      "loss": 0.8709,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": 1.7643026113510132,
+      "rewards/margins": 1.6466624736785889,
+      "rewards/rejected": 0.1176399439573288,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.7467175306295647e-07,
+      "logits/chosen": -2.6879727840423584,
+      "logits/rejected": -2.660984516143799,
+      "logps/chosen": -296.12017822265625,
+      "logps/rejected": -265.49176025390625,
+      "loss": 0.8715,
+      "rewards/accuracies": 0.6812499761581421,
+      "rewards/chosen": 1.2846415042877197,
+      "rewards/margins": 1.6656051874160767,
+      "rewards/rejected": -0.38096341490745544,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.6604720940421207e-07,
+      "logits/chosen": -2.6495959758758545,
+      "logits/rejected": -2.633176803588867,
+      "logps/chosen": -285.0,
+      "logps/rejected": -238.13760375976562,
+      "loss": 0.9971,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.48344117403030396,
+      "rewards/margins": 1.2780396938323975,
+      "rewards/rejected": -0.7945985198020935,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.5626458262912735e-07,
+      "logits/chosen": -2.6688625812530518,
+      "logits/rejected": -2.661983013153076,
+      "logps/chosen": -276.2964172363281,
+      "logps/rejected": -271.0657043457031,
+      "loss": 0.9757,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": -0.47159165143966675,
+      "rewards/margins": 0.9514617919921875,
+      "rewards/rejected": -1.4230536222457886,
+      "step": 130
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.453763107901675e-07,
+      "logits/chosen": -2.720446825027466,
+      "logits/rejected": -2.721700429916382,
+      "logps/chosen": -296.03277587890625,
+      "logps/rejected": -267.8554992675781,
+      "loss": 0.7556,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": 0.4882308542728424,
+      "rewards/margins": 1.5448472499847412,
+      "rewards/rejected": -1.0566164255142212,
+      "step": 140
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.3344075855595097e-07,
+      "logits/chosen": -2.6869354248046875,
+      "logits/rejected": -2.678093433380127,
+      "logps/chosen": -282.30657958984375,
+      "logps/rejected": -251.81973266601562,
+      "loss": 1.4312,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.9246972799301147,
+      "rewards/margins": 2.1031014919281006,
+      "rewards/rejected": -0.1784040927886963,
+      "step": 150
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.2052190435769554e-07,
+      "logits/chosen": -2.644658088684082,
+      "logits/rejected": -2.618086099624634,
+      "logps/chosen": -279.2743835449219,
+      "logps/rejected": -268.9571228027344,
+      "loss": 0.8955,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 2.6602110862731934,
+      "rewards/margins": 2.369070053100586,
+      "rewards/rejected": 0.29114121198654175,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.0668899744407567e-07,
+      "logits/chosen": -2.6654858589172363,
+      "logits/rejected": -2.6409499645233154,
+      "logps/chosen": -262.2958984375,
+      "logps/rejected": -229.4518585205078,
+      "loss": 1.0858,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.36875656247138977,
+      "rewards/margins": 1.1033318042755127,
+      "rewards/rejected": -0.7345751523971558,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.920161866827889e-07,
+      "logits/chosen": -2.6779518127441406,
+      "logits/rejected": -2.694640636444092,
+      "logps/chosen": -276.3097229003906,
+      "logps/rejected": -262.0291442871094,
+      "loss": 1.0793,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": 1.123580813407898,
+      "rewards/margins": 2.2866923809051514,
+      "rewards/rejected": -1.1631114482879639,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.765821230985757e-07,
+      "logits/chosen": -2.6965956687927246,
+      "logits/rejected": -2.6685996055603027,
+      "logps/chosen": -267.73687744140625,
+      "logps/rejected": -259.35357666015625,
+      "loss": 0.8591,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": 0.6378843784332275,
+      "rewards/margins": 1.7748029232025146,
+      "rewards/rejected": -1.1369187831878662,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.604695382782159e-07,
+      "logits/chosen": -2.6755518913269043,
+      "logits/rejected": -2.6578094959259033,
+      "logps/chosen": -290.0172424316406,
+      "logps/rejected": -252.45919799804688,
+      "loss": 0.9481,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.05484447628259659,
+      "rewards/margins": 2.1967554092407227,
+      "rewards/rejected": -2.141911029815674,
+      "step": 200
+    },
+    {
+      "epoch": 0.42,
+      "eval_logits/chosen": -2.7043323516845703,
+      "eval_logits/rejected": -2.6753692626953125,
+      "eval_logps/chosen": -284.77410888671875,
+      "eval_logps/rejected": -264.4426574707031,
+      "eval_loss": 0.9532725214958191,
+      "eval_rewards/accuracies": 0.716269850730896,
+      "eval_rewards/chosen": -0.6643804311752319,
+      "eval_rewards/margins": 1.9997262954711914,
+      "eval_rewards/rejected": -2.664106607437134,
+      "eval_runtime": 236.1755,
+      "eval_samples_per_second": 8.468,
+      "eval_steps_per_second": 0.267,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.4376480090239047e-07,
+      "logits/chosen": -2.712965726852417,
+      "logits/rejected": -2.6518542766571045,
+      "logps/chosen": -289.49072265625,
+      "logps/rejected": -262.79595947265625,
+      "loss": 0.8643,
+      "rewards/accuracies": 0.684374988079071,
+      "rewards/chosen": -0.5081722140312195,
+      "rewards/margins": 1.8118541240692139,
+      "rewards/rejected": -2.320026397705078,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.265574537815398e-07,
+      "logits/chosen": -2.6325292587280273,
+      "logits/rejected": -2.629293918609619,
+      "logps/chosen": -259.7528076171875,
+      "logps/rejected": -245.0424346923828,
+      "loss": 0.9605,
+      "rewards/accuracies": 0.6343749761581421,
+      "rewards/chosen": 0.8424679040908813,
+      "rewards/margins": 1.7455743551254272,
+      "rewards/rejected": -0.9031065702438354,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.0893973387735683e-07,
+      "logits/chosen": -2.5948872566223145,
+      "logits/rejected": -2.583383798599243,
+      "logps/chosen": -263.6277770996094,
+      "logps/rejected": -252.355224609375,
+      "loss": 0.9994,
+      "rewards/accuracies": 0.6656249761581421,
+      "rewards/chosen": 0.9661090970039368,
+      "rewards/margins": 3.1072936058044434,
+      "rewards/rejected": -2.1411845684051514,
+      "step": 230
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.910060778827554e-07,
+      "logits/chosen": -2.631458044052124,
+      "logits/rejected": -2.603405714035034,
+      "logps/chosen": -264.26947021484375,
+      "logps/rejected": -245.29733276367188,
+      "loss": 1.0716,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 1.2004565000534058,
+      "rewards/margins": 1.8289244174957275,
+      "rewards/rejected": -0.6284679174423218,
+      "step": 240
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.7285261601056697e-07,
+      "logits/chosen": -2.6394925117492676,
+      "logits/rejected": -2.6251111030578613,
+      "logps/chosen": -272.2856750488281,
+      "logps/rejected": -250.0095672607422,
+      "loss": 0.9656,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": 1.3560218811035156,
+      "rewards/margins": 1.9196758270263672,
+      "rewards/rejected": -0.5636539459228516,
+      "step": 250
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.5457665670441937e-07,
+      "logits/chosen": -2.651275396347046,
+      "logits/rejected": -2.6304633617401123,
+      "logps/chosen": -280.27410888671875,
+      "logps/rejected": -252.9152374267578,
+      "loss": 1.0543,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": -0.03507481887936592,
+      "rewards/margins": 1.2433618307113647,
+      "rewards/rejected": -1.2784364223480225,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.3627616503391812e-07,
+      "logits/chosen": -2.6496596336364746,
+      "logits/rejected": -2.6472182273864746,
+      "logps/chosen": -288.3260498046875,
+      "logps/rejected": -280.3363037109375,
+      "loss": 0.9168,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": 0.828028678894043,
+      "rewards/margins": 2.5466268062591553,
+      "rewards/rejected": -1.7185981273651123,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.1804923757009882e-07,
+      "logits/chosen": -2.661709785461426,
+      "logits/rejected": -2.6548213958740234,
+      "logps/chosen": -267.2577819824219,
+      "logps/rejected": -241.8800048828125,
+      "loss": 1.1955,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": 0.9889399409294128,
+      "rewards/margins": 2.1581242084503174,
+      "rewards/rejected": -1.1691839694976807,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9999357655598891e-07,
+      "logits/chosen": -2.6423428058624268,
+      "logits/rejected": -2.6236939430236816,
+      "logps/chosen": -274.1272277832031,
+      "logps/rejected": -249.1870880126953,
+      "loss": 1.2642,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.9026322364807129,
+      "rewards/margins": 1.699610948562622,
+      "rewards/rejected": -0.7969785332679749,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8220596619089573e-07,
+      "logits/chosen": -2.637317419052124,
+      "logits/rejected": -2.597743034362793,
+      "logps/chosen": -298.6712951660156,
+      "logps/rejected": -295.92657470703125,
+      "loss": 1.1698,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": 0.8392047882080078,
+      "rewards/margins": 1.0658338069915771,
+      "rewards/rejected": -0.22662897408008575,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.647817538357072e-07,
+      "logits/chosen": -2.6557185649871826,
+      "logits/rejected": -2.6295552253723145,
+      "logps/chosen": -273.03802490234375,
+      "logps/rejected": -228.7330322265625,
+      "loss": 0.9258,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 0.48593106865882874,
+      "rewards/margins": 1.9354314804077148,
+      "rewards/rejected": -1.4495004415512085,
+      "step": 310
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.478143389201113e-07,
+      "logits/chosen": -2.5909767150878906,
+      "logits/rejected": -2.5993030071258545,
+      "logps/chosen": -272.3155212402344,
+      "logps/rejected": -257.76409912109375,
+      "loss": 0.8658,
+      "rewards/accuracies": 0.7281249761581421,
+      "rewards/chosen": 0.7982915043830872,
+      "rewards/margins": 2.247641086578369,
+      "rewards/rejected": -1.4493494033813477,
+      "step": 320
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.3139467229135998e-07,
+      "logits/chosen": -2.705423355102539,
+      "logits/rejected": -2.7025485038757324,
+      "logps/chosen": -302.91082763671875,
+      "logps/rejected": -265.9149475097656,
+      "loss": 0.9932,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 1.026079773902893,
+      "rewards/margins": 2.0061373710632324,
+      "rewards/rejected": -0.9800575971603394,
+      "step": 330
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.1561076868822755e-07,
+      "logits/chosen": -2.610400438308716,
+      "logits/rejected": -2.614844560623169,
+      "logps/chosen": -271.6020812988281,
+      "logps/rejected": -254.05477905273438,
+      "loss": 0.965,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 0.7108423113822937,
+      "rewards/margins": 1.3122758865356445,
+      "rewards/rejected": -0.6014334559440613,
+      "step": 340
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.0054723495346482e-07,
+      "logits/chosen": -2.616030216217041,
+      "logits/rejected": -2.5651869773864746,
+      "logps/chosen": -256.9847106933594,
+      "logps/rejected": -244.5271453857422,
+      "loss": 0.9356,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.8414610028266907,
+      "rewards/margins": 2.031790018081665,
+      "rewards/rejected": -1.1903290748596191,
+      "step": 350
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.628481651367875e-08,
+      "logits/chosen": -2.6491808891296387,
+      "logits/rejected": -2.6336731910705566,
+      "logps/chosen": -297.15911865234375,
+      "logps/rejected": -255.7582550048828,
+      "loss": 0.8238,
+      "rewards/accuracies": 0.690625011920929,
+      "rewards/chosen": 1.010446310043335,
+      "rewards/margins": 3.2363944053649902,
+      "rewards/rejected": -2.2259488105773926,
+      "step": 360
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.289996455765748e-08,
+      "logits/chosen": -2.619288206100464,
+      "logits/rejected": -2.616589069366455,
+      "logps/chosen": -307.8691711425781,
+      "logps/rejected": -256.36322021484375,
+      "loss": 1.0289,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.2276843786239624,
+      "rewards/margins": 2.0671706199645996,
+      "rewards/rejected": -0.8394859433174133,
+      "step": 370
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.046442623320145e-08,
+      "logits/chosen": -2.6064088344573975,
+      "logits/rejected": -2.617523431777954,
+      "logps/chosen": -279.7250061035156,
+      "logps/rejected": -265.47808837890625,
+      "loss": 0.9126,
+      "rewards/accuracies": 0.671875,
+      "rewards/chosen": 1.0034754276275635,
+      "rewards/margins": 1.880950927734375,
+      "rewards/rejected": -0.8774752616882324,
+      "step": 380
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.904486005914027e-08,
+      "logits/chosen": -2.626131534576416,
+      "logits/rejected": -2.612278461456299,
+      "logps/chosen": -274.55963134765625,
+      "logps/rejected": -268.88525390625,
+      "loss": 0.9176,
+      "rewards/accuracies": 0.6968749761581421,
+      "rewards/chosen": 0.5394259691238403,
+      "rewards/margins": 1.4705688953399658,
+      "rewards/rejected": -0.9311429858207703,
+      "step": 390
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.8702478614051345e-08,
+      "logits/chosen": -2.6065127849578857,
+      "logits/rejected": -2.5645954608917236,
+      "logps/chosen": -320.189208984375,
+      "logps/rejected": -285.04571533203125,
+      "loss": 1.0499,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.5851168632507324,
+      "rewards/margins": 2.4354395866394043,
+      "rewards/rejected": -1.8503224849700928,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "eval_logits/chosen": -2.6585872173309326,
+      "eval_logits/rejected": -2.6278274059295654,
+      "eval_logps/chosen": -283.5934753417969,
+      "eval_logps/rejected": -263.3767395019531,
+      "eval_loss": 0.8541988134384155,
+      "eval_rewards/accuracies": 0.6765872836112976,
+      "eval_rewards/chosen": 0.5162815451622009,
+      "eval_rewards/margins": 2.114495038986206,
+      "eval_rewards/rejected": -1.5982133150100708,
+      "eval_runtime": 236.3982,
+      "eval_samples_per_second": 8.46,
+      "eval_steps_per_second": 0.266,
+      "step": 400
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.9492720416985e-08,
+      "logits/chosen": -2.5927202701568604,
+      "logits/rejected": -2.6027348041534424,
+      "logps/chosen": -265.5550537109375,
+      "logps/rejected": -238.1681365966797,
+      "loss": 0.9647,
+      "rewards/accuracies": 0.703125,
+      "rewards/chosen": 0.5153275728225708,
+      "rewards/margins": 1.5753355026245117,
+      "rewards/rejected": -1.060007929801941,
+      "step": 410
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.1464952759020856e-08,
+      "logits/chosen": -2.587930679321289,
+      "logits/rejected": -2.5975794792175293,
+      "logps/chosen": -280.38665771484375,
+      "logps/rejected": -264.66094970703125,
+      "loss": 0.9527,
+      "rewards/accuracies": 0.715624988079071,
+      "rewards/chosen": 0.6154674291610718,
+      "rewards/margins": 2.1581873893737793,
+      "rewards/rejected": -1.542720079421997,
+      "step": 420
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.4662207078575684e-08,
+      "logits/chosen": -2.6294283866882324,
+      "logits/rejected": -2.6279261112213135,
+      "logps/chosen": -288.611572265625,
+      "logps/rejected": -249.09817504882812,
+      "loss": 0.9541,
+      "rewards/accuracies": 0.690625011920929,
+      "rewards/chosen": 0.7420939207077026,
+      "rewards/margins": 1.885738730430603,
+      "rewards/rejected": -1.14364492893219,
+      "step": 430
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.12094829893642e-09,
+      "logits/chosen": -2.6458382606506348,
+      "logits/rejected": -2.6251447200775146,
+      "logps/chosen": -259.57086181640625,
+      "logps/rejected": -250.9589080810547,
+      "loss": 0.9229,
+      "rewards/accuracies": 0.721875011920929,
+      "rewards/chosen": 0.9782251119613647,
+      "rewards/margins": 2.130990982055664,
+      "rewards/rejected": -1.1527659893035889,
+      "step": 440
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.8708793644441086e-09,
+      "logits/chosen": -2.6016457080841064,
+      "logits/rejected": -2.5447189807891846,
+      "logps/chosen": -281.54058837890625,
+      "logps/rejected": -276.61578369140625,
+      "loss": 0.8586,
+      "rewards/accuracies": 0.7093750238418579,
+      "rewards/chosen": 0.8872340321540833,
+      "rewards/margins": 2.6381373405456543,
+      "rewards/rejected": -1.7509028911590576,
+      "step": 450
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.9347820230782295e-09,
+      "logits/chosen": -2.627577781677246,
+      "logits/rejected": -2.5947518348693848,
+      "logps/chosen": -270.9955139160156,
+      "logps/rejected": -251.592529296875,
+      "loss": 0.8516,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.6147862672805786,
+      "rewards/margins": 2.4109296798706055,
+      "rewards/rejected": -1.7961437702178955,
+      "step": 460
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.2839470889836627e-10,
+      "logits/chosen": -2.6408920288085938,
+      "logits/rejected": -2.6343941688537598,
+      "logps/chosen": -300.63250732421875,
+      "logps/rejected": -269.65399169921875,
+      "loss": 0.7941,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": 0.6158030033111572,
+      "rewards/margins": 2.596193790435791,
+      "rewards/rejected": -1.9803907871246338,
+      "step": 470
+    },
+    {
+      "epoch": 1.0,
+      "step": 477,
+      "total_flos": 0.0,
+      "train_loss": 0.9276265908087324,
+      "train_runtime": 18165.5867,
+      "train_samples_per_second": 3.365,
+      "train_steps_per_second": 0.026
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 477,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 900,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8203df1bfbd322a4a13a8b8e424f4ac2339feee6e857731e3d46f50c9258869
+oid sha256:0176702234bba928ce8b68a81b241f65f819b968d1d227521e394d69f291410d
 size 5944