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: 0.4969
+- Rewards/chosen: -1.1626
+- Rewards/rejected: -2.1853
+- Rewards/accuracies: 0.7773
+- Rewards/margins: 1.0227
+- Logps/rejected: -481.1959
+- Logps/chosen: -378.8522
+- Logits/rejected: 1.4928
+- Logits/chosen: 0.5873
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5632        | 0.2092 | 100  | 0.5684          | -0.8769        | -1.4450          | 0.7305             | 0.5681          | -407.1669      | -350.2800    | -0.3489         | -0.6128       |
+| 0.5374        | 0.4184 | 200  | 0.5202          | -0.7727        | -1.5477          | 0.7852             | 0.7750          | -417.4406      | -339.8678    | -0.1011         | -0.6617       |
+| 0.4826        | 0.6276 | 300  | 0.5018          | -1.1013        | -2.0815          | 0.7734             | 0.9802          | -470.8159      | -372.7218    | 1.3131          | 0.4518        |
+| 0.495         | 0.8368 | 400  | 0.4969          | -1.1626        | -2.1853          | 0.7773             | 1.0227          | -481.1959      | -378.8522    | 1.4928          | 0.5873        |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.5340489398485447,
+    "train_runtime": 7520.1807,
+    "train_samples": 61134,
+    "train_samples_per_second": 8.129,
+    "train_steps_per_second": 0.064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566bff0ec661fec8f828663bef68e7162c9f30a4a9d678f00d79402950395038
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071f62f7eccae4daa97a875d63185c5f60f851c33bd0d79e92efcfa4e53fbfd3
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353bff0bfe0de90a832913816d2b1919b4db9ef50435ec0ca76c75f0845cb767
+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/Apr26_18-03-59_n136-098-146/events.out.tfevents.1714137440.n136-098-146.2262128.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bddd5577979976fa6f7a862a33fe0bb3b7d4b783ce85648da1b10ca496da573
-size 35841
+oid sha256:33dcbf842c898231ebd42d44931d75d69bdebc9b8e02cc54ceab484995271ebe
+size 41011

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.5340489398485447,
+    "train_runtime": 7520.1807,
+    "train_samples": 61134,
+    "train_samples_per_second": 8.129,
+    "train_steps_per_second": 0.064
+}

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": 9.298505033829334,
+      "learning_rate": 1.0416666666666666e-08,
+      "logits/chosen": -2.7660439014434814,
+      "logits/rejected": -2.717564582824707,
+      "logps/chosen": -269.8568420410156,
+      "logps/rejected": -360.52459716796875,
+      "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": 9.201570340284004,
+      "learning_rate": 1.0416666666666667e-07,
+      "logits/chosen": -2.592160224914551,
+      "logits/rejected": -2.562696695327759,
+      "logps/chosen": -264.77496337890625,
+      "logps/rejected": -251.57083129882812,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.4513888955116272,
+      "rewards/chosen": 0.0002292051794938743,
+      "rewards/margins": 0.00040812836959958076,
+      "rewards/rejected": -0.00017892329196911305,
+      "step": 10
+    },
+    {
+      "epoch": 0.04184100418410042,
+      "grad_norm": 8.403210934524289,
+      "learning_rate": 2.0833333333333333e-07,
+      "logits/chosen": -2.653189182281494,
+      "logits/rejected": -2.605264663696289,
+      "logps/chosen": -281.4413146972656,
+      "logps/rejected": -296.7750244140625,
+      "loss": 0.6923,
+      "rewards/accuracies": 0.53125,
+      "rewards/chosen": 0.0011203143512830138,
+      "rewards/margins": 0.0008017805521376431,
+      "rewards/rejected": 0.000318533944664523,
+      "step": 20
+    },
+    {
+      "epoch": 0.06276150627615062,
+      "grad_norm": 8.307511730281874,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -2.6639485359191895,
+      "logits/rejected": -2.5914711952209473,
+      "logps/chosen": -299.44439697265625,
+      "logps/rejected": -263.6602478027344,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.668749988079071,
+      "rewards/chosen": 0.012274232693016529,
+      "rewards/margins": 0.009375235997140408,
+      "rewards/rejected": 0.002898997161537409,
+      "step": 30
+    },
+    {
+      "epoch": 0.08368200836820083,
+      "grad_norm": 8.23101419584969,
+      "learning_rate": 4.1666666666666667e-07,
+      "logits/chosen": -2.5564517974853516,
+      "logits/rejected": -2.5212883949279785,
+      "logps/chosen": -263.17132568359375,
+      "logps/rejected": -245.1162109375,
+      "loss": 0.6774,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": 0.03954031318426132,
+      "rewards/margins": 0.04678243398666382,
+      "rewards/rejected": -0.007242122199386358,
+      "step": 40
+    },
+    {
+      "epoch": 0.10460251046025104,
+      "grad_norm": 8.47834585122089,
+      "learning_rate": 4.999733114418725e-07,
+      "logits/chosen": -2.495573043823242,
+      "logits/rejected": -2.4556243419647217,
+      "logps/chosen": -279.73748779296875,
+      "logps/rejected": -297.7320251464844,
+      "loss": 0.6609,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -5.648513251799159e-05,
+      "rewards/margins": 0.049422554671764374,
+      "rewards/rejected": -0.04947904497385025,
+      "step": 50
+    },
+    {
+      "epoch": 0.12552301255230125,
+      "grad_norm": 11.447029638220144,
+      "learning_rate": 4.990398100856366e-07,
+      "logits/chosen": -2.5056962966918945,
+      "logits/rejected": -2.4333505630493164,
+      "logps/chosen": -274.71142578125,
+      "logps/rejected": -314.40966796875,
+      "loss": 0.6378,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -0.03104892373085022,
+      "rewards/margins": 0.13223406672477722,
+      "rewards/rejected": -0.16328299045562744,
+      "step": 60
+    },
+    {
+      "epoch": 0.14644351464435146,
+      "grad_norm": 13.212333314905758,
+      "learning_rate": 4.967775735898179e-07,
+      "logits/chosen": -2.325637102127075,
+      "logits/rejected": -2.3246896266937256,
+      "logps/chosen": -266.88873291015625,
+      "logps/rejected": -277.4853515625,
+      "loss": 0.6211,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -0.012722762301564217,
+      "rewards/margins": 0.1949584186077118,
+      "rewards/rejected": -0.20768117904663086,
+      "step": 70
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 24.02513624388519,
+      "learning_rate": 4.931986719649298e-07,
+      "logits/chosen": -2.423210859298706,
+      "logits/rejected": -2.316833019256592,
+      "logps/chosen": -340.6246643066406,
+      "logps/rejected": -308.7874755859375,
+      "loss": 0.599,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.17806725203990936,
+      "rewards/margins": 0.26922112703323364,
+      "rewards/rejected": -0.4472884237766266,
+      "step": 80
+    },
+    {
+      "epoch": 0.18828451882845187,
+      "grad_norm": 21.808882527816824,
+      "learning_rate": 4.883222001996351e-07,
+      "logits/chosen": -1.0463552474975586,
+      "logits/rejected": -0.8626599311828613,
+      "logps/chosen": -330.01776123046875,
+      "logps/rejected": -381.9994812011719,
+      "loss": 0.5615,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -0.7090646028518677,
+      "rewards/margins": 0.5869495868682861,
+      "rewards/rejected": -1.2960141897201538,
+      "step": 90
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 19.245462836155387,
+      "learning_rate": 4.821741763807186e-07,
+      "logits/chosen": -0.5482389330863953,
+      "logits/rejected": -0.278412789106369,
+      "logps/chosen": -338.76251220703125,
+      "logps/rejected": -393.6160888671875,
+      "loss": 0.5632,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.7840398550033569,
+      "rewards/margins": 0.5818365216255188,
+      "rewards/rejected": -1.3658764362335205,
+      "step": 100
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "eval_logits/chosen": -0.6127901673316956,
+      "eval_logits/rejected": -0.3488583564758301,
+      "eval_logps/chosen": -350.2799987792969,
+      "eval_logps/rejected": -407.1668701171875,
+      "eval_loss": 0.5684163570404053,
+      "eval_rewards/accuracies": 0.73046875,
+      "eval_rewards/chosen": -0.8768651485443115,
+      "eval_rewards/margins": 0.5681313276290894,
+      "eval_rewards/rejected": -1.4449963569641113,
+      "eval_runtime": 96.8146,
+      "eval_samples_per_second": 20.658,
+      "eval_steps_per_second": 0.331,
+      "step": 100
+    },
+    {
+      "epoch": 0.2301255230125523,
+      "grad_norm": 22.525663230437072,
+      "learning_rate": 4.747874028753375e-07,
+      "logits/chosen": -0.790797233581543,
+      "logits/rejected": -0.19812031090259552,
+      "logps/chosen": -387.7721862792969,
+      "logps/rejected": -402.75067138671875,
+      "loss": 0.5625,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.8319207429885864,
+      "rewards/margins": 0.617226779460907,
+      "rewards/rejected": -1.4491477012634277,
+      "step": 110
+    },
+    {
+      "epoch": 0.2510460251046025,
+      "grad_norm": 21.93406688438369,
+      "learning_rate": 4.662012913161997e-07,
+      "logits/chosen": -0.1478520929813385,
+      "logits/rejected": 0.21510139107704163,
+      "logps/chosen": -376.58184814453125,
+      "logps/rejected": -419.5226135253906,
+      "loss": 0.5426,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.9541470408439636,
+      "rewards/margins": 0.6425132155418396,
+      "rewards/rejected": -1.5966601371765137,
+      "step": 120
+    },
+    {
+      "epoch": 0.2719665271966527,
+      "grad_norm": 21.863413590534076,
+      "learning_rate": 4.5646165232345103e-07,
+      "logits/chosen": 0.039292819797992706,
+      "logits/rejected": 0.5163652300834656,
+      "logps/chosen": -377.03961181640625,
+      "logps/rejected": -429.0581970214844,
+      "loss": 0.524,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.9503645896911621,
+      "rewards/margins": 0.6558589339256287,
+      "rewards/rejected": -1.606223464012146,
+      "step": 130
+    },
+    {
+      "epoch": 0.2928870292887029,
+      "grad_norm": 21.169176355822128,
+      "learning_rate": 4.456204510851956e-07,
+      "logits/chosen": -0.4013391435146332,
+      "logits/rejected": -0.08902309834957123,
+      "logps/chosen": -390.9994201660156,
+      "logps/rejected": -439.9606018066406,
+      "loss": 0.532,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.7503399848937988,
+      "rewards/margins": 0.6424974203109741,
+      "rewards/rejected": -1.3928372859954834,
+      "step": 140
+    },
+    {
+      "epoch": 0.3138075313807531,
+      "grad_norm": 24.525761488765827,
+      "learning_rate": 4.337355301007335e-07,
+      "logits/chosen": -0.0023450672160834074,
+      "logits/rejected": 0.44477328658103943,
+      "logps/chosen": -398.7283630371094,
+      "logps/rejected": -448.65374755859375,
+      "loss": 0.5354,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.155042052268982,
+      "rewards/margins": 0.5694054365158081,
+      "rewards/rejected": -1.7244476079940796,
+      "step": 150
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 22.353019803776466,
+      "learning_rate": 4.2087030056579986e-07,
+      "logits/chosen": -0.20696048438549042,
+      "logits/rejected": 0.4880790710449219,
+      "logps/chosen": -360.6669921875,
+      "logps/rejected": -434.037353515625,
+      "loss": 0.5315,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.8759892582893372,
+      "rewards/margins": 0.8901454210281372,
+      "rewards/rejected": -1.7661348581314087,
+      "step": 160
+    },
+    {
+      "epoch": 0.35564853556485354,
+      "grad_norm": 25.914625948890546,
+      "learning_rate": 4.070934040463998e-07,
+      "logits/chosen": 0.6924982666969299,
+      "logits/rejected": 1.1295397281646729,
+      "logps/chosen": -374.10723876953125,
+      "logps/rejected": -420.09588623046875,
+      "loss": 0.5363,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.247719645500183,
+      "rewards/margins": 0.6419915556907654,
+      "rewards/rejected": -1.8897111415863037,
+      "step": 170
+    },
+    {
+      "epoch": 0.37656903765690375,
+      "grad_norm": 21.366817652532127,
+      "learning_rate": 3.9247834624635404e-07,
+      "logits/chosen": 0.7046024203300476,
+      "logits/rejected": 1.3452444076538086,
+      "logps/chosen": -360.4297180175781,
+      "logps/rejected": -401.1781005859375,
+      "loss": 0.5038,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.040706753730774,
+      "rewards/margins": 0.6953631639480591,
+      "rewards/rejected": -1.7360700368881226,
+      "step": 180
+    },
+    {
+      "epoch": 0.39748953974895396,
+      "grad_norm": 24.086446407003773,
+      "learning_rate": 3.7710310482256523e-07,
+      "logits/chosen": -0.14418189227581024,
+      "logits/rejected": 0.45502132177352905,
+      "logps/chosen": -359.0705261230469,
+      "logps/rejected": -413.5692443847656,
+      "loss": 0.512,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.8782768249511719,
+      "rewards/margins": 0.6598676443099976,
+      "rewards/rejected": -1.5381444692611694,
+      "step": 190
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "grad_norm": 64.3318645589766,
+      "learning_rate": 3.610497133404795e-07,
+      "logits/chosen": -0.16302886605262756,
+      "logits/rejected": 0.2976584732532501,
+      "logps/chosen": -352.27783203125,
+      "logps/rejected": -425.39825439453125,
+      "loss": 0.5374,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.9238117933273315,
+      "rewards/margins": 0.8096807599067688,
+      "rewards/rejected": -1.7334924936294556,
+      "step": 200
+    },
+    {
+      "epoch": 0.41841004184100417,
+      "eval_logits/chosen": -0.661653995513916,
+      "eval_logits/rejected": -0.10106822848320007,
+      "eval_logps/chosen": -339.8678283691406,
+      "eval_logps/rejected": -417.4406433105469,
+      "eval_loss": 0.5201992988586426,
+      "eval_rewards/accuracies": 0.78515625,
+      "eval_rewards/chosen": -0.7727437615394592,
+      "eval_rewards/margins": 0.7749909162521362,
+      "eval_rewards/rejected": -1.5477344989776611,
+      "eval_runtime": 96.6072,
+      "eval_samples_per_second": 20.702,
+      "eval_steps_per_second": 0.331,
+      "step": 200
+    },
+    {
+      "epoch": 0.4393305439330544,
+      "grad_norm": 27.061409181894096,
+      "learning_rate": 3.4440382358952115e-07,
+      "logits/chosen": 0.0046714721247553825,
+      "logits/rejected": 0.9609675407409668,
+      "logps/chosen": -385.9021301269531,
+      "logps/rejected": -421.04376220703125,
+      "loss": 0.5291,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.9620998501777649,
+      "rewards/margins": 0.7358611822128296,
+      "rewards/rejected": -1.6979610919952393,
+      "step": 210
+    },
+    {
+      "epoch": 0.4602510460251046,
+      "grad_norm": 30.2004484482118,
+      "learning_rate": 3.272542485937368e-07,
+      "logits/chosen": 1.2403850555419922,
+      "logits/rejected": 2.167426586151123,
+      "logps/chosen": -388.68963623046875,
+      "logps/rejected": -451.56854248046875,
+      "loss": 0.5153,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.2331252098083496,
+      "rewards/margins": 0.8259220123291016,
+      "rewards/rejected": -2.059047222137451,
+      "step": 220
+    },
+    {
+      "epoch": 0.4811715481171548,
+      "grad_norm": 20.504102481838405,
+      "learning_rate": 3.096924887558854e-07,
+      "logits/chosen": -0.1779499053955078,
+      "logits/rejected": 0.3767474591732025,
+      "logps/chosen": -345.39398193359375,
+      "logps/rejected": -434.6441345214844,
+      "loss": 0.5204,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.9652854204177856,
+      "rewards/margins": 0.9037777185440063,
+      "rewards/rejected": -1.869063138961792,
+      "step": 230
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 25.85435210721558,
+      "learning_rate": 2.9181224366319943e-07,
+      "logits/chosen": 0.048077814280986786,
+      "logits/rejected": 0.7805795669555664,
+      "logps/chosen": -367.3824768066406,
+      "logps/rejected": -432.07232666015625,
+      "loss": 0.4979,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.0368225574493408,
+      "rewards/margins": 0.7932166457176208,
+      "rewards/rejected": -1.8300392627716064,
+      "step": 240
+    },
+    {
+      "epoch": 0.5230125523012552,
+      "grad_norm": 24.42587136099329,
+      "learning_rate": 2.7370891215954565e-07,
+      "logits/chosen": 0.673697829246521,
+      "logits/rejected": 1.6910991668701172,
+      "logps/chosen": -414.1255798339844,
+      "logps/rejected": -471.29949951171875,
+      "loss": 0.5001,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1593507528305054,
+      "rewards/margins": 0.9584181904792786,
+      "rewards/rejected": -2.117769241333008,
+      "step": 250
+    },
+    {
+      "epoch": 0.5439330543933054,
+      "grad_norm": 27.657368894192487,
+      "learning_rate": 2.55479083351317e-07,
+      "logits/chosen": 0.624454140663147,
+      "logits/rejected": 1.5941022634506226,
+      "logps/chosen": -408.07598876953125,
+      "logps/rejected": -454.6495666503906,
+      "loss": 0.5019,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1376445293426514,
+      "rewards/margins": 0.8690470457077026,
+      "rewards/rejected": -2.0066916942596436,
+      "step": 260
+    },
+    {
+      "epoch": 0.5648535564853556,
+      "grad_norm": 21.64156582174747,
+      "learning_rate": 2.3722002126275822e-07,
+      "logits/chosen": 0.22647273540496826,
+      "logits/rejected": 0.885449230670929,
+      "logps/chosen": -374.7611999511719,
+      "logps/rejected": -424.3587951660156,
+      "loss": 0.5157,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -0.9776525497436523,
+      "rewards/margins": 0.6894922256469727,
+      "rewards/rejected": -1.667145013809204,
+      "step": 270
+    },
+    {
+      "epoch": 0.5857740585774058,
+      "grad_norm": 28.159079517918425,
+      "learning_rate": 2.19029145890313e-07,
+      "logits/chosen": 0.3553857207298279,
+      "logits/rejected": 1.404651403427124,
+      "logps/chosen": -366.23333740234375,
+      "logps/rejected": -431.8450622558594,
+      "loss": 0.5305,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.045562505722046,
+      "rewards/margins": 0.8510251045227051,
+      "rewards/rejected": -1.896587610244751,
+      "step": 280
+    },
+    {
+      "epoch": 0.606694560669456,
+      "grad_norm": 23.668357833413996,
+      "learning_rate": 2.0100351342479216e-07,
+      "logits/chosen": 0.38658827543258667,
+      "logits/rejected": 1.411795973777771,
+      "logps/chosen": -377.20208740234375,
+      "logps/rejected": -449.6202697753906,
+      "loss": 0.5079,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.2611474990844727,
+      "rewards/margins": 0.8154961466789246,
+      "rewards/rejected": -2.076643466949463,
+      "step": 290
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "grad_norm": 25.399079532767146,
+      "learning_rate": 1.8323929841460178e-07,
+      "logits/chosen": 0.3453945219516754,
+      "logits/rejected": 1.5490226745605469,
+      "logps/chosen": -423.813720703125,
+      "logps/rejected": -465.08514404296875,
+      "loss": 0.4826,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.2281761169433594,
+      "rewards/margins": 0.821620762348175,
+      "rewards/rejected": -2.0497965812683105,
+      "step": 300
+    },
+    {
+      "epoch": 0.6276150627615062,
+      "eval_logits/chosen": 0.4518190026283264,
+      "eval_logits/rejected": 1.3131211996078491,
+      "eval_logps/chosen": -372.7217712402344,
+      "eval_logps/rejected": -470.81585693359375,
+      "eval_loss": 0.5018269419670105,
+      "eval_rewards/accuracies": 0.7734375,
+      "eval_rewards/chosen": -1.101283073425293,
+      "eval_rewards/margins": 0.98020339012146,
+      "eval_rewards/rejected": -2.081486701965332,
+      "eval_runtime": 96.5631,
+      "eval_samples_per_second": 20.712,
+      "eval_steps_per_second": 0.331,
+      "step": 300
+    },
+    {
+      "epoch": 0.6485355648535565,
+      "grad_norm": 33.32118469948312,
+      "learning_rate": 1.6583128063291573e-07,
+      "logits/chosen": 0.7086529731750488,
+      "logits/rejected": 1.432820439338684,
+      "logps/chosen": -417.11456298828125,
+      "logps/rejected": -465.49871826171875,
+      "loss": 0.4857,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.2177866697311401,
+      "rewards/margins": 0.8520353436470032,
+      "rewards/rejected": -2.069821834564209,
+      "step": 310
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 32.370966943547394,
+      "learning_rate": 1.488723393865766e-07,
+      "logits/chosen": 0.8957827687263489,
+      "logits/rejected": 1.8967578411102295,
+      "logps/chosen": -423.543212890625,
+      "logps/rejected": -458.0819396972656,
+      "loss": 0.4785,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.2987310886383057,
+      "rewards/margins": 0.8338556289672852,
+      "rewards/rejected": -2.1325864791870117,
+      "step": 320
+    },
+    {
+      "epoch": 0.6903765690376569,
+      "grad_norm": 31.730308695137953,
+      "learning_rate": 1.3245295796480788e-07,
+      "logits/chosen": 0.5041384100914001,
+      "logits/rejected": 1.5472161769866943,
+      "logps/chosen": -390.4256286621094,
+      "logps/rejected": -465.3321228027344,
+      "loss": 0.4858,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.2821542024612427,
+      "rewards/margins": 0.7761803269386292,
+      "rewards/rejected": -2.0583345890045166,
+      "step": 330
+    },
+    {
+      "epoch": 0.7112970711297071,
+      "grad_norm": 32.601240272025024,
+      "learning_rate": 1.1666074087171627e-07,
+      "logits/chosen": 0.5397793054580688,
+      "logits/rejected": 1.506024956703186,
+      "logps/chosen": -407.0556335449219,
+      "logps/rejected": -500.10662841796875,
+      "loss": 0.4937,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.1706117391586304,
+      "rewards/margins": 1.0300366878509521,
+      "rewards/rejected": -2.200648784637451,
+      "step": 340
+    },
+    {
+      "epoch": 0.7322175732217573,
+      "grad_norm": 27.635567277748542,
+      "learning_rate": 1.0157994641835734e-07,
+      "logits/chosen": 0.6218138933181763,
+      "logits/rejected": 1.4956554174423218,
+      "logps/chosen": -377.9348449707031,
+      "logps/rejected": -454.3216857910156,
+      "loss": 0.4706,
+      "rewards/accuracies": 0.7562500238418579,
+      "rewards/chosen": -1.1972359418869019,
+      "rewards/margins": 0.9388922452926636,
+      "rewards/rejected": -2.1361279487609863,
+      "step": 350
+    },
+    {
+      "epoch": 0.7531380753138075,
+      "grad_norm": 24.687045320186403,
+      "learning_rate": 8.729103716819111e-08,
+      "logits/chosen": 0.6358219385147095,
+      "logits/rejected": 1.956719994544983,
+      "logps/chosen": -429.2447814941406,
+      "logps/rejected": -485.86962890625,
+      "loss": 0.5022,
+      "rewards/accuracies": 0.78125,
+      "rewards/chosen": -1.265527367591858,
+      "rewards/margins": 0.9801186323165894,
+      "rewards/rejected": -2.2456459999084473,
+      "step": 360
+    },
+    {
+      "epoch": 0.7740585774058577,
+      "grad_norm": 28.11584433716017,
+      "learning_rate": 7.387025063449081e-08,
+      "logits/chosen": 1.1712688207626343,
+      "logits/rejected": 2.0544753074645996,
+      "logps/chosen": -422.5091247558594,
+      "logps/rejected": -463.7154846191406,
+      "loss": 0.5029,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.4717609882354736,
+      "rewards/margins": 0.7830532193183899,
+      "rewards/rejected": -2.254814386367798,
+      "step": 370
+    },
+    {
+      "epoch": 0.7949790794979079,
+      "grad_norm": 24.476287038588072,
+      "learning_rate": 6.138919252022435e-08,
+      "logits/chosen": 1.362653374671936,
+      "logits/rejected": 2.166234016418457,
+      "logps/chosen": -396.3254699707031,
+      "logps/rejected": -516.1082153320312,
+      "loss": 0.4967,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.5684077739715576,
+      "rewards/margins": 1.005509614944458,
+      "rewards/rejected": -2.5739173889160156,
+      "step": 380
+    },
+    {
+      "epoch": 0.8158995815899581,
+      "grad_norm": 26.234400494581838,
+      "learning_rate": 4.991445467064689e-08,
+      "logits/chosen": 0.9196502566337585,
+      "logits/rejected": 1.507375955581665,
+      "logps/chosen": -442.8583984375,
+      "logps/rejected": -509.21148681640625,
+      "loss": 0.4846,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.372214913368225,
+      "rewards/margins": 0.8801954388618469,
+      "rewards/rejected": -2.252410411834717,
+      "step": 390
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 27.121453974144618,
+      "learning_rate": 3.9507259776993954e-08,
+      "logits/chosen": 1.0388725996017456,
+      "logits/rejected": 2.068740129470825,
+      "logps/chosen": -408.56390380859375,
+      "logps/rejected": -501.59442138671875,
+      "loss": 0.495,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.3802869319915771,
+      "rewards/margins": 0.9655326008796692,
+      "rewards/rejected": -2.3458199501037598,
+      "step": 400
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "eval_logits/chosen": 0.5873361825942993,
+      "eval_logits/rejected": 1.4928171634674072,
+      "eval_logps/chosen": -378.8522033691406,
+      "eval_logps/rejected": -481.19586181640625,
+      "eval_loss": 0.496925413608551,
+      "eval_rewards/accuracies": 0.77734375,
+      "eval_rewards/chosen": -1.1625876426696777,
+      "eval_rewards/margins": 1.0226988792419434,
+      "eval_rewards/rejected": -2.1852867603302,
+      "eval_runtime": 96.4494,
+      "eval_samples_per_second": 20.736,
+      "eval_steps_per_second": 0.332,
+      "step": 400
+    },
+    {
+      "epoch": 0.8577405857740585,
+      "grad_norm": 25.996039172593594,
+      "learning_rate": 3.022313472693447e-08,
+      "logits/chosen": 0.6017621159553528,
+      "logits/rejected": 1.8573381900787354,
+      "logps/chosen": -425.21923828125,
+      "logps/rejected": -486.6591796875,
+      "loss": 0.503,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.2630172967910767,
+      "rewards/margins": 0.9154027700424194,
+      "rewards/rejected": -2.178420305252075,
+      "step": 410
+    },
+    {
+      "epoch": 0.8786610878661087,
+      "grad_norm": 23.551777016650735,
+      "learning_rate": 2.2111614344599684e-08,
+      "logits/chosen": 0.4802716374397278,
+      "logits/rejected": 1.373286247253418,
+      "logps/chosen": -415.99517822265625,
+      "logps/rejected": -479.66845703125,
+      "loss": 0.4934,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.1892141103744507,
+      "rewards/margins": 0.862848162651062,
+      "rewards/rejected": -2.0520622730255127,
+      "step": 420
+    },
+    {
+      "epoch": 0.899581589958159,
+      "grad_norm": 26.58253060605497,
+      "learning_rate": 1.521597710086439e-08,
+      "logits/chosen": 0.9357998967170715,
+      "logits/rejected": 1.944998025894165,
+      "logps/chosen": -411.1884765625,
+      "logps/rejected": -484.83062744140625,
+      "loss": 0.4727,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.3215035200119019,
+      "rewards/margins": 0.9490026235580444,
+      "rewards/rejected": -2.2705063819885254,
+      "step": 430
+    },
+    {
+      "epoch": 0.9205020920502092,
+      "grad_norm": 29.91389949643719,
+      "learning_rate": 9.57301420397924e-09,
+      "logits/chosen": 0.5421011447906494,
+      "logits/rejected": 1.6035425662994385,
+      "logps/chosen": -402.51129150390625,
+      "logps/rejected": -472.44708251953125,
+      "loss": 0.4901,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.181741714477539,
+      "rewards/margins": 0.8516114950180054,
+      "rewards/rejected": -2.033353328704834,
+      "step": 440
+    },
+    {
+      "epoch": 0.9414225941422594,
+      "grad_norm": 25.77219458607021,
+      "learning_rate": 5.212833302556258e-09,
+      "logits/chosen": 0.6684173941612244,
+      "logits/rejected": 1.5389642715454102,
+      "logps/chosen": -420.6578063964844,
+      "logps/rejected": -521.8568725585938,
+      "loss": 0.4916,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.269736409187317,
+      "rewards/margins": 0.8780879974365234,
+      "rewards/rejected": -2.147824287414551,
+      "step": 450
+    },
+    {
+      "epoch": 0.9623430962343096,
+      "grad_norm": 25.79146794601895,
+      "learning_rate": 2.158697848236607e-09,
+      "logits/chosen": 0.8310929536819458,
+      "logits/rejected": 1.7648357152938843,
+      "logps/chosen": -395.16680908203125,
+      "logps/rejected": -452.0589294433594,
+      "loss": 0.4942,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.2320220470428467,
+      "rewards/margins": 0.8616892695426941,
+      "rewards/rejected": -2.0937113761901855,
+      "step": 460
+    },
+    {
+      "epoch": 0.9832635983263598,
+      "grad_norm": 25.562634206457844,
+      "learning_rate": 4.269029751107489e-10,
+      "logits/chosen": 0.6654651761054993,
+      "logits/rejected": 1.765618920326233,
+      "logps/chosen": -397.56622314453125,
+      "logps/rejected": -492.461181640625,
+      "loss": 0.4831,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.1886755228042603,
+      "rewards/margins": 0.9124252200126648,
+      "rewards/rejected": -2.1011009216308594,
+      "step": 470
+    },
+    {
+      "epoch": 1.0,
+      "step": 478,
+      "total_flos": 0.0,
+      "train_loss": 0.5340489398485447,
+      "train_runtime": 7520.1807,
+      "train_samples_per_second": 8.129,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "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
+}