Model save

README.md

@@ -0,0 +1,73 @@
+---
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: selective-pairrm-32754820
+  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. -->
+
+# selective-pairrm-32754820
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7284
+- Rewards/chosen: -2.3186
+- Rewards/rejected: -2.4353
+- Rewards/accuracies: 0.5703
+- Rewards/margins: 0.1167
+- Logps/rejected: -555.1447
+- Logps/chosen: -524.2090
+- Logits/rejected: -2.5947
+- Logits/chosen: -2.5961
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5696        | 0.32  | 100  | 0.7351          | -2.0420        | -2.1261          | 0.5781             | 0.0841          | -524.2233      | -496.5468    | -2.5568         | -2.5577       |
+| 0.5384        | 0.64  | 200  | 0.7274          | -2.2166        | -2.3279          | 0.5781             | 0.1113          | -544.4059      | -514.0054    | -2.6227         | -2.6242       |
+| 0.5331        | 0.96  | 300  | 0.7288          | -2.3199        | -2.4365          | 0.5703             | 0.1166          | -555.2662      | -524.3375    | -2.5949         | -2.5963       |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.596123456954956,
+    "eval_logits/rejected": -2.594705104827881,
+    "eval_logps/chosen": -524.208984375,
+    "eval_logps/rejected": -555.1446533203125,
+    "eval_loss": 0.7283747792243958,
+    "eval_rewards/accuracies": 0.5703125,
+    "eval_rewards/chosen": -2.3185923099517822,
+    "eval_rewards/margins": 0.11669808626174927,
+    "eval_rewards/rejected": -2.435290575027466,
+    "eval_runtime": 128.6637,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 7.772,
+    "eval_steps_per_second": 0.249,
+    "train_loss": 0.5676067341596652,
+    "train_runtime": 5367.57,
+    "train_samples": 19996,
+    "train_samples_per_second": 3.725,
+    "train_steps_per_second": 0.058
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.596123456954956,
+    "eval_logits/rejected": -2.594705104827881,
+    "eval_logps/chosen": -524.208984375,
+    "eval_logps/rejected": -555.1446533203125,
+    "eval_loss": 0.7283747792243958,
+    "eval_rewards/accuracies": 0.5703125,
+    "eval_rewards/chosen": -2.3185923099517822,
+    "eval_rewards/margins": 0.11669808626174927,
+    "eval_rewards/rejected": -2.435290575027466,
+    "eval_runtime": 128.6637,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 7.772,
+    "eval_steps_per_second": 0.249
+}

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 sha256:252c35d32ce1cd2fab2c62e3aef5606f41c47fa003b1302d04f8a65cece1dc9a
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48dc47e48e172fb7c89e2518cc687d29e1f2c2443192483d8469186f1ba4ab30
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c4be8eaa8c15922c68674c949c81ed0d17c64e4c05cb1ac256a993e95a0234
+size 4540516344

model.safetensors.index.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5676067341596652,
+    "train_runtime": 5367.57,
+    "train_samples": 19996,
+    "train_samples_per_second": 3.725,
+    "train_steps_per_second": 0.058
+}

trainer_state.json

@@ -0,0 +1,526 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 100,
+  "global_step": 312,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.5625e-08,
+      "logits/chosen": -2.700185537338257,
+      "logits/rejected": -2.688293933868408,
+      "logps/chosen": -259.16033935546875,
+      "logps/rejected": -294.7476501464844,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.5624999999999999e-07,
+      "logits/chosen": -2.666435718536377,
+      "logits/rejected": -2.655320644378662,
+      "logps/chosen": -265.0631103515625,
+      "logps/rejected": -312.2701721191406,
+      "loss": 0.693,
+      "rewards/accuracies": 0.4861111044883728,
+      "rewards/chosen": 0.0003658923669718206,
+      "rewards/margins": 0.0006390429334715009,
+      "rewards/rejected": -0.0002731506247073412,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.1249999999999997e-07,
+      "logits/chosen": -2.6772429943084717,
+      "logits/rejected": -2.6626598834991455,
+      "logps/chosen": -269.0950927734375,
+      "logps/rejected": -325.16937255859375,
+      "loss": 0.6919,
+      "rewards/accuracies": 0.6187499761581421,
+      "rewards/chosen": 0.0031788970809429884,
+      "rewards/margins": 0.0032460358925163746,
+      "rewards/rejected": -6.713894981658086e-05,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.6874999999999996e-07,
+      "logits/chosen": -2.630918502807617,
+      "logits/rejected": -2.631808280944824,
+      "logps/chosen": -255.07919311523438,
+      "logps/rejected": -299.809326171875,
+      "loss": 0.686,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.012466179206967354,
+      "rewards/margins": 0.01523002702742815,
+      "rewards/rejected": -0.0027638464234769344,
+      "step": 30
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.989935734988097e-07,
+      "logits/chosen": -2.6304612159729004,
+      "logits/rejected": -2.6413488388061523,
+      "logps/chosen": -261.91748046875,
+      "logps/rejected": -311.5315856933594,
+      "loss": 0.6721,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": 0.0007823005435056984,
+      "rewards/margins": 0.04043162614107132,
+      "rewards/rejected": -0.03964932635426521,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.949188496058089e-07,
+      "logits/chosen": -2.65004563331604,
+      "logits/rejected": -2.6387436389923096,
+      "logps/chosen": -268.8555603027344,
+      "logps/rejected": -323.8399658203125,
+      "loss": 0.6422,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": -0.11418936401605606,
+      "rewards/margins": 0.10296630859375,
+      "rewards/rejected": -0.21715569496154785,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.877641290737883e-07,
+      "logits/chosen": -2.5872256755828857,
+      "logits/rejected": -2.5944290161132812,
+      "logps/chosen": -328.38861083984375,
+      "logps/rejected": -406.2428894042969,
+      "loss": 0.6032,
+      "rewards/accuracies": 0.731249988079071,
+      "rewards/chosen": -0.560045599937439,
+      "rewards/margins": 0.22636902332305908,
+      "rewards/rejected": -0.786414623260498,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.776193866647039e-07,
+      "logits/chosen": -2.5252180099487305,
+      "logits/rejected": -2.547880172729492,
+      "logps/chosen": -422.89495849609375,
+      "logps/rejected": -511.3482360839844,
+      "loss": 0.5848,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -1.3909833431243896,
+      "rewards/margins": 0.39587897062301636,
+      "rewards/rejected": -1.7868623733520508,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.646121984004665e-07,
+      "logits/chosen": -2.536372661590576,
+      "logits/rejected": -2.5390119552612305,
+      "logps/chosen": -448.7959899902344,
+      "logps/rejected": -541.9494018554688,
+      "loss": 0.5717,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.8497803211212158,
+      "rewards/margins": 0.4831104874610901,
+      "rewards/rejected": -2.332890748977661,
+      "step": 80
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.489061372204452e-07,
+      "logits/chosen": -2.5548112392425537,
+      "logits/rejected": -2.5604214668273926,
+      "logps/chosen": -474.6028747558594,
+      "logps/rejected": -563.7825927734375,
+      "loss": 0.5595,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.9470739364624023,
+      "rewards/margins": 0.4594634175300598,
+      "rewards/rejected": -2.4065375328063965,
+      "step": 90
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.3069871595684787e-07,
+      "logits/chosen": -2.6011409759521484,
+      "logits/rejected": -2.6057095527648926,
+      "logps/chosen": -450.83514404296875,
+      "logps/rejected": -538.4827880859375,
+      "loss": 0.5696,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.824249029159546,
+      "rewards/margins": 0.5003727674484253,
+      "rewards/rejected": -2.3246216773986816,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "eval_logits/chosen": -2.557655096054077,
+      "eval_logits/rejected": -2.556790590286255,
+      "eval_logps/chosen": -496.5467529296875,
+      "eval_logps/rejected": -524.2233276367188,
+      "eval_loss": 0.7350802421569824,
+      "eval_rewards/accuracies": 0.578125,
+      "eval_rewards/chosen": -2.0419702529907227,
+      "eval_rewards/margins": 0.0841071680188179,
+      "eval_rewards/rejected": -2.12607741355896,
+      "eval_runtime": 129.4654,
+      "eval_samples_per_second": 7.724,
+      "eval_steps_per_second": 0.247,
+      "step": 100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.10218903496256e-07,
+      "logits/chosen": -2.562108278274536,
+      "logits/rejected": -2.56473708152771,
+      "logps/chosen": -462.493408203125,
+      "logps/rejected": -540.7071533203125,
+      "loss": 0.567,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.7570621967315674,
+      "rewards/margins": 0.41273313760757446,
+      "rewards/rejected": -2.169795274734497,
+      "step": 110
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.877242453630256e-07,
+      "logits/chosen": -2.5863144397735596,
+      "logits/rejected": -2.5731258392333984,
+      "logps/chosen": -429.6874084472656,
+      "logps/rejected": -528.7286376953125,
+      "loss": 0.5481,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.5704660415649414,
+      "rewards/margins": 0.4964219033718109,
+      "rewards/rejected": -2.0668880939483643,
+      "step": 120
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.634976249348867e-07,
+      "logits/chosen": -2.6673202514648438,
+      "logits/rejected": -2.671137809753418,
+      "logps/chosen": -422.5250549316406,
+      "logps/rejected": -522.568115234375,
+      "loss": 0.5535,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.60529363155365,
+      "rewards/margins": 0.516074538230896,
+      "rewards/rejected": -2.121368169784546,
+      "step": 130
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.378437060203357e-07,
+      "logits/chosen": -2.584428071975708,
+      "logits/rejected": -2.577939033508301,
+      "logps/chosen": -461.6734924316406,
+      "logps/rejected": -583.6375732421875,
+      "loss": 0.5498,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.7603881359100342,
+      "rewards/margins": 0.5440183877944946,
+      "rewards/rejected": -2.3044066429138184,
+      "step": 140
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.110851015344735e-07,
+      "logits/chosen": -2.6381332874298096,
+      "logits/rejected": -2.646150588989258,
+      "logps/chosen": -460.08465576171875,
+      "logps/rejected": -574.1367797851562,
+      "loss": 0.5495,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.9179586172103882,
+      "rewards/margins": 0.5406409502029419,
+      "rewards/rejected": -2.45859956741333,
+      "step": 150
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.8355831645441387e-07,
+      "logits/chosen": -2.5772454738616943,
+      "logits/rejected": -2.5750832557678223,
+      "logps/chosen": -468.78472900390625,
+      "logps/rejected": -560.0062255859375,
+      "loss": 0.5689,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -1.913264513015747,
+      "rewards/margins": 0.4484502673149109,
+      "rewards/rejected": -2.3617148399353027,
+      "step": 160
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.5560951607395126e-07,
+      "logits/chosen": -2.6182687282562256,
+      "logits/rejected": -2.632976531982422,
+      "logps/chosen": -443.65643310546875,
+      "logps/rejected": -542.0991821289062,
+      "loss": 0.5757,
+      "rewards/accuracies": 0.706250011920929,
+      "rewards/chosen": -1.7725292444229126,
+      "rewards/margins": 0.4888339936733246,
+      "rewards/rejected": -2.2613632678985596,
+      "step": 170
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.2759017277414164e-07,
+      "logits/chosen": -2.643632411956787,
+      "logits/rejected": -2.641953945159912,
+      "logps/chosen": -442.72943115234375,
+      "logps/rejected": -540.6067504882812,
+      "loss": 0.5452,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -1.7243016958236694,
+      "rewards/margins": 0.5064828395843506,
+      "rewards/rejected": -2.2307846546173096,
+      "step": 180
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.998526460541818e-07,
+      "logits/chosen": -2.6374473571777344,
+      "logits/rejected": -2.62355375289917,
+      "logps/chosen": -445.89117431640625,
+      "logps/rejected": -565.252685546875,
+      "loss": 0.5218,
+      "rewards/accuracies": 0.793749988079071,
+      "rewards/chosen": -1.6967271566390991,
+      "rewards/margins": 0.6666227579116821,
+      "rewards/rejected": -2.363349676132202,
+      "step": 190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7274575140626315e-07,
+      "logits/chosen": -2.6294193267822266,
+      "logits/rejected": -2.6281723976135254,
+      "logps/chosen": -417.04278564453125,
+      "logps/rejected": -500.09014892578125,
+      "loss": 0.5384,
+      "rewards/accuracies": 0.6937500238418579,
+      "rewards/chosen": -1.653368353843689,
+      "rewards/margins": 0.43656763434410095,
+      "rewards/rejected": -2.0899360179901123,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "eval_logits/chosen": -2.6241683959960938,
+      "eval_logits/rejected": -2.6227188110351562,
+      "eval_logps/chosen": -514.0054321289062,
+      "eval_logps/rejected": -544.4058837890625,
+      "eval_loss": 0.7274174094200134,
+      "eval_rewards/accuracies": 0.578125,
+      "eval_rewards/chosen": -2.216557264328003,
+      "eval_rewards/margins": 0.11134582757949829,
+      "eval_rewards/rejected": -2.3279030323028564,
+      "eval_runtime": 128.5445,
+      "eval_samples_per_second": 7.779,
+      "eval_steps_per_second": 0.249,
+      "step": 200
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.4661037375836987e-07,
+      "logits/chosen": -2.632556438446045,
+      "logits/rejected": -2.628350257873535,
+      "logps/chosen": -449.53631591796875,
+      "logps/rejected": -564.7415161132812,
+      "loss": 0.5509,
+      "rewards/accuracies": 0.768750011920929,
+      "rewards/chosen": -1.8155481815338135,
+      "rewards/margins": 0.5979192852973938,
+      "rewards/rejected": -2.4134674072265625,
+      "step": 210
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.2177518064852348e-07,
+      "logits/chosen": -2.606738567352295,
+      "logits/rejected": -2.6152873039245605,
+      "logps/chosen": -459.555908203125,
+      "logps/rejected": -574.1082763671875,
+      "loss": 0.5255,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.91512930393219,
+      "rewards/margins": 0.6077762842178345,
+      "rewards/rejected": -2.5229055881500244,
+      "step": 220
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.855248903979505e-08,
+      "logits/chosen": -2.6100919246673584,
+      "logits/rejected": -2.615342617034912,
+      "logps/chosen": -455.86907958984375,
+      "logps/rejected": -566.136474609375,
+      "loss": 0.5274,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.8699758052825928,
+      "rewards/margins": 0.6331700682640076,
+      "rewards/rejected": -2.503145694732666,
+      "step": 230
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.723433775328384e-08,
+      "logits/chosen": -2.5851168632507324,
+      "logits/rejected": -2.584052562713623,
+      "logps/chosen": -442.36669921875,
+      "logps/rejected": -545.6100463867188,
+      "loss": 0.5468,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.8480392694473267,
+      "rewards/margins": 0.548007607460022,
+      "rewards/rejected": -2.3960468769073486,
+      "step": 240
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.808881491049722e-08,
+      "logits/chosen": -2.58274245262146,
+      "logits/rejected": -2.589717149734497,
+      "logps/chosen": -436.4042053222656,
+      "logps/rejected": -545.1051025390625,
+      "loss": 0.5157,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.793677568435669,
+      "rewards/margins": 0.5883136987686157,
+      "rewards/rejected": -2.381991147994995,
+      "step": 250
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.1356686569674335e-08,
+      "logits/chosen": -2.5628256797790527,
+      "logits/rejected": -2.5696637630462646,
+      "logps/chosen": -454.79168701171875,
+      "logps/rejected": -577.7164916992188,
+      "loss": 0.5253,
+      "rewards/accuracies": 0.7437499761581421,
+      "rewards/chosen": -1.8464300632476807,
+      "rewards/margins": 0.6209232211112976,
+      "rewards/rejected": -2.467353582382202,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.724836895290805e-08,
+      "logits/chosen": -2.6082510948181152,
+      "logits/rejected": -2.610037326812744,
+      "logps/chosen": -428.15850830078125,
+      "logps/rejected": -547.8997192382812,
+      "loss": 0.4924,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": -1.7478383779525757,
+      "rewards/margins": 0.6664589643478394,
+      "rewards/rejected": -2.414297342300415,
+      "step": 270
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5941282340065697e-08,
+      "logits/chosen": -2.575770616531372,
+      "logits/rejected": -2.579246997833252,
+      "logps/chosen": -476.03106689453125,
+      "logps/rejected": -600.0574340820312,
+      "loss": 0.521,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.9693467617034912,
+      "rewards/margins": 0.6460846662521362,
+      "rewards/rejected": -2.615431308746338,
+      "step": 280
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.577619905828281e-09,
+      "logits/chosen": -2.5882465839385986,
+      "logits/rejected": -2.5952746868133545,
+      "logps/chosen": -436.7637634277344,
+      "logps/rejected": -548.1011962890625,
+      "loss": 0.5357,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.8334407806396484,
+      "rewards/margins": 0.622291088104248,
+      "rewards/rejected": -2.4557318687438965,
+      "step": 290
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.2625595580163247e-09,
+      "logits/chosen": -2.5985870361328125,
+      "logits/rejected": -2.5904204845428467,
+      "logps/chosen": -484.90325927734375,
+      "logps/rejected": -618.5193481445312,
+      "loss": 0.5331,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -2.0060954093933105,
+      "rewards/margins": 0.6673663854598999,
+      "rewards/rejected": -2.673461675643921,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "eval_logits/chosen": -2.596346378326416,
+      "eval_logits/rejected": -2.5948848724365234,
+      "eval_logps/chosen": -524.3374633789062,
+      "eval_logps/rejected": -555.2661743164062,
+      "eval_loss": 0.7287929654121399,
+      "eval_rewards/accuracies": 0.5703125,
+      "eval_rewards/chosen": -2.3198771476745605,
+      "eval_rewards/margins": 0.11662794649600983,
+      "eval_rewards/rejected": -2.4365055561065674,
+      "eval_runtime": 128.3827,
+      "eval_samples_per_second": 7.789,
+      "eval_steps_per_second": 0.249,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.294126437336733e-11,
+      "logits/chosen": -2.6014821529388428,
+      "logits/rejected": -2.595231533050537,
+      "logps/chosen": -469.10955810546875,
+      "logps/rejected": -573.4671630859375,
+      "loss": 0.544,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.9832292795181274,
+      "rewards/margins": 0.540331244468689,
+      "rewards/rejected": -2.5235605239868164,
+      "step": 310
+    },
+    {
+      "epoch": 1.0,
+      "step": 312,
+      "total_flos": 0.0,
+      "train_loss": 0.5676067341596652,
+      "train_runtime": 5367.57,
+      "train_samples_per_second": 3.725,
+      "train_steps_per_second": 0.058
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 312,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}