Model save

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+base_model: Minbyul/biomistral-7b-wo-kqa_golden-iter-dpo-step2
+tags:
+- trl
+- dpo
+- generated_from_trainer
+model-index:
+- name: biomistral-7b-wo-kqa_golden-iter-dpo-step3
+  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. -->
+
+# biomistral-7b-wo-kqa_golden-iter-dpo-step3
+
+This model is a fine-tuned version of [Minbyul/biomistral-7b-wo-kqa_golden-iter-dpo-step2](https://huggingface.co/Minbyul/biomistral-7b-wo-kqa_golden-iter-dpo-step2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Logits/chosen: -0.8589
+- Logits/rejected: -1.5130
+- Logps/chosen: -39.0432
+- Logps/rejected: -58.7210
+- Loss: 0.6837
+- Rewards/accuracies: 0.6400
+- Rewards/chosen: -0.0394
+- Rewards/margins: 0.0267
+- Rewards/rejected: -0.0661
+
+## 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: 1e-07
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- 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 | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
+|:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
+| 0.6794        | 0.37  | 100  | -0.8266       | -1.4757         | -35.5860     | -53.0765       | 0.6906          | 0.5900             | -0.0048        | 0.0048          | -0.0096          |
+| 0.6555        | 0.74  | 200  | -0.8589       | -1.5130         | -39.0432     | -58.7210       | 0.6837          | 0.6400             | -0.0394        | 0.0267          | -0.0661          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.1692200431117305,
+    "train_runtime": 798.9647,
+    "train_samples": 17264,
+    "train_samples_per_second": 21.608,
+    "train_steps_per_second": 0.338
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce409cff4722b9a731610eee4285f50c9f2d5b36cf9e7d2481b206ae57402a9
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8187324d72ff88a59d6bc9c26004792edd0b87978a47298a811599baa6429504
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53d580d5ce1226972d503f03c4c98a758c0b21e66e24742d3e4d812d193cc5d
+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": 0.1692200431117305,
+    "train_runtime": 798.9647,
+    "train_samples": 17264,
+    "train_samples_per_second": 21.608,
+    "train_steps_per_second": 0.338
+}

trainer_state.json

@@ -0,0 +1,482 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 41.70182769977995,
+      "learning_rate": 3.703703703703703e-09,
+      "logits/chosen": -1.5467987060546875,
+      "logits/rejected": -1.308578372001648,
+      "logps/chosen": -37.12041473388672,
+      "logps/rejected": -61.68842315673828,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 37.047557637653945,
+      "learning_rate": 3.7037037037037036e-08,
+      "logits/chosen": -0.9453011751174927,
+      "logits/rejected": -1.405588984489441,
+      "logps/chosen": -28.646324157714844,
+      "logps/rejected": -40.27184295654297,
+      "loss": 0.693,
+      "rewards/accuracies": 0.4930555522441864,
+      "rewards/chosen": -0.00016396207502111793,
+      "rewards/margins": 0.001127531286329031,
+      "rewards/rejected": -0.0012914934195578098,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 38.71986120422308,
+      "learning_rate": 7.407407407407407e-08,
+      "logits/chosen": -1.144275188446045,
+      "logits/rejected": -1.4153748750686646,
+      "logps/chosen": -38.298439025878906,
+      "logps/rejected": -41.69558334350586,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.5625,
+      "rewards/chosen": 0.0009220183710567653,
+      "rewards/margins": 0.0017043445259332657,
+      "rewards/rejected": -0.0007823262130841613,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 39.765817458266895,
+      "learning_rate": 9.99623976252115e-08,
+      "logits/chosen": -0.8312944173812866,
+      "logits/rejected": -1.4380576610565186,
+      "logps/chosen": -32.726478576660156,
+      "logps/rejected": -43.810638427734375,
+      "loss": 0.6925,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.001944520859979093,
+      "rewards/margins": 0.0023826442193239927,
+      "rewards/rejected": -0.00043812341755256057,
+      "step": 30
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 35.39090968218046,
+      "learning_rate": 9.929548316723981e-08,
+      "logits/chosen": -1.0166804790496826,
+      "logits/rejected": -1.4055747985839844,
+      "logps/chosen": -31.433521270751953,
+      "logps/rejected": -46.84731674194336,
+      "loss": 0.6915,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 0.0015541177708655596,
+      "rewards/margins": 0.002054566517472267,
+      "rewards/rejected": -0.0005004488630220294,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 42.118488242592456,
+      "learning_rate": 9.780577808869398e-08,
+      "logits/chosen": -1.0024656057357788,
+      "logits/rejected": -1.3138850927352905,
+      "logps/chosen": -30.340801239013672,
+      "logps/rejected": -43.08925247192383,
+      "loss": 0.6905,
+      "rewards/accuracies": 0.606249988079071,
+      "rewards/chosen": 0.0033007909078150988,
+      "rewards/margins": 0.003635294735431671,
+      "rewards/rejected": -0.000334503740305081,
+      "step": 50
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 36.92382364235435,
+      "learning_rate": 9.551814704830733e-08,
+      "logits/chosen": -1.1217851638793945,
+      "logits/rejected": -1.4166934490203857,
+      "logps/chosen": -31.992273330688477,
+      "logps/rejected": -46.66759490966797,
+      "loss": 0.6886,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.008065198548138142,
+      "rewards/margins": 0.010263124480843544,
+      "rewards/rejected": -0.0021979263983666897,
+      "step": 60
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 39.24669749459966,
+      "learning_rate": 9.247077288236486e-08,
+      "logits/chosen": -0.9909595251083374,
+      "logits/rejected": -1.514561653137207,
+      "logps/chosen": -31.16408348083496,
+      "logps/rejected": -57.032684326171875,
+      "loss": 0.6863,
+      "rewards/accuracies": 0.71875,
+      "rewards/chosen": 0.009227448143064976,
+      "rewards/margins": 0.01421318482607603,
+      "rewards/rejected": -0.004985739476978779,
+      "step": 70
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 38.72478614258279,
+      "learning_rate": 8.871451929520661e-08,
+      "logits/chosen": -0.7630345225334167,
+      "logits/rejected": -1.5050407648086548,
+      "logps/chosen": -25.78152084350586,
+      "logps/rejected": -38.437538146972656,
+      "loss": 0.6839,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.013479883782565594,
+      "rewards/margins": 0.018440086394548416,
+      "rewards/rejected": -0.004960204008966684,
+      "step": 80
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 35.63155458414573,
+      "learning_rate": 8.431208189343668e-08,
+      "logits/chosen": -0.8956977725028992,
+      "logits/rejected": -1.463505506515503,
+      "logps/chosen": -30.033924102783203,
+      "logps/rejected": -56.11266326904297,
+      "loss": 0.6827,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.013467254117131233,
+      "rewards/margins": 0.022690553218126297,
+      "rewards/rejected": -0.00922329816967249,
+      "step": 90
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 37.21064690820017,
+      "learning_rate": 7.93369417339209e-08,
+      "logits/chosen": -0.7459134459495544,
+      "logits/rejected": -1.5061514377593994,
+      "logps/chosen": -28.494699478149414,
+      "logps/rejected": -49.45507049560547,
+      "loss": 0.6794,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.015813838690519333,
+      "rewards/margins": 0.02535676583647728,
+      "rewards/rejected": -0.009542929008603096,
+      "step": 100
+    },
+    {
+      "epoch": 0.37,
+      "eval_logits/chosen": -0.8265538215637207,
+      "eval_logits/rejected": -1.4756767749786377,
+      "eval_logps/chosen": -35.586036682128906,
+      "eval_logps/rejected": -53.076499938964844,
+      "eval_loss": 0.6905515193939209,
+      "eval_rewards/accuracies": 0.5899999737739563,
+      "eval_rewards/chosen": -0.004811165854334831,
+      "eval_rewards/margins": 0.004816049709916115,
+      "eval_rewards/rejected": -0.009627215564250946,
+      "eval_runtime": 65.669,
+      "eval_samples_per_second": 11.954,
+      "eval_steps_per_second": 0.381,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 41.489362342224126,
+      "learning_rate": 7.387213885189744e-08,
+      "logits/chosen": -0.9582328796386719,
+      "logits/rejected": -1.4757133722305298,
+      "logps/chosen": -29.652179718017578,
+      "logps/rejected": -51.44434356689453,
+      "loss": 0.6783,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.01538840215653181,
+      "rewards/margins": 0.030315887182950974,
+      "rewards/rejected": -0.014927484095096588,
+      "step": 110
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 34.811996422375785,
+      "learning_rate": 6.800888624023552e-08,
+      "logits/chosen": -1.1017180681228638,
+      "logits/rejected": -1.2910267114639282,
+      "logps/chosen": -34.17676544189453,
+      "logps/rejected": -47.27839660644531,
+      "loss": 0.6752,
+      "rewards/accuracies": 0.8062499761581421,
+      "rewards/chosen": 0.019322626292705536,
+      "rewards/margins": 0.03619503602385521,
+      "rewards/rejected": -0.01687241531908512,
+      "step": 120
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 36.517002002282,
+      "learning_rate": 6.184504741390595e-08,
+      "logits/chosen": -1.0513687133789062,
+      "logits/rejected": -1.4773876667022705,
+      "logps/chosen": -30.05930519104004,
+      "logps/rejected": -49.12663269042969,
+      "loss": 0.6722,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": 0.017959367483854294,
+      "rewards/margins": 0.038190923631191254,
+      "rewards/rejected": -0.02023155428469181,
+      "step": 130
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 45.92150266428131,
+      "learning_rate": 5.5483502970626584e-08,
+      "logits/chosen": -1.0855646133422852,
+      "logits/rejected": -1.4738510847091675,
+      "logps/chosen": -35.4333610534668,
+      "logps/rejected": -48.60808563232422,
+      "loss": 0.6713,
+      "rewards/accuracies": 0.893750011920929,
+      "rewards/chosen": 0.01625698432326317,
+      "rewards/margins": 0.04006917029619217,
+      "rewards/rejected": -0.023812180384993553,
+      "step": 140
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 52.17233360297021,
+      "learning_rate": 4.9030433411408785e-08,
+      "logits/chosen": -1.0967937707901,
+      "logits/rejected": -1.4282653331756592,
+      "logps/chosen": -27.93039321899414,
+      "logps/rejected": -48.556251525878906,
+      "loss": 0.6666,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.01784222200512886,
+      "rewards/margins": 0.05219421908259392,
+      "rewards/rejected": -0.03435199707746506,
+      "step": 150
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 36.1012077969649,
+      "learning_rate": 4.259354688243757e-08,
+      "logits/chosen": -1.088585615158081,
+      "logits/rejected": -1.4759548902511597,
+      "logps/chosen": -30.474609375,
+      "logps/rejected": -50.4084358215332,
+      "loss": 0.668,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.007844483479857445,
+      "rewards/margins": 0.05492537096142769,
+      "rewards/rejected": -0.04708089306950569,
+      "step": 160
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 39.4057901333892,
+      "learning_rate": 3.628028141903493e-08,
+      "logits/chosen": -1.1803226470947266,
+      "logits/rejected": -1.41080641746521,
+      "logps/chosen": -32.83087158203125,
+      "logps/rejected": -45.69880676269531,
+      "loss": 0.6612,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.01473814807832241,
+      "rewards/margins": 0.06375907361507416,
+      "rewards/rejected": -0.0490209236741066,
+      "step": 170
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 38.966283555722626,
+      "learning_rate": 3.0196011698042156e-08,
+      "logits/chosen": -1.0210983753204346,
+      "logits/rejected": -1.4852098226547241,
+      "logps/chosen": -29.679798126220703,
+      "logps/rejected": -50.24894332885742,
+      "loss": 0.6648,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": 0.006426820065826178,
+      "rewards/margins": 0.06615011394023895,
+      "rewards/rejected": -0.059723298996686935,
+      "step": 180
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 40.704072746648535,
+      "learning_rate": 2.444229022970634e-08,
+      "logits/chosen": -0.9898138046264648,
+      "logits/rejected": -1.4493308067321777,
+      "logps/chosen": -29.71084976196289,
+      "logps/rejected": -52.1125602722168,
+      "loss": 0.6587,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.005389463622123003,
+      "rewards/margins": 0.06682445108890533,
+      "rewards/rejected": -0.06143498420715332,
+      "step": 190
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 48.9298479981709,
+      "learning_rate": 1.9115152345327152e-08,
+      "logits/chosen": -1.0230295658111572,
+      "logits/rejected": -1.5533816814422607,
+      "logps/chosen": -30.142093658447266,
+      "logps/rejected": -58.23160934448242,
+      "loss": 0.6555,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": 0.004340417217463255,
+      "rewards/margins": 0.08527159690856934,
+      "rewards/rejected": -0.08093118667602539,
+      "step": 200
+    },
+    {
+      "epoch": 0.74,
+      "eval_logits/chosen": -0.8588806390762329,
+      "eval_logits/rejected": -1.5130012035369873,
+      "eval_logps/chosen": -39.04316711425781,
+      "eval_logps/rejected": -58.72098159790039,
+      "eval_loss": 0.6837000846862793,
+      "eval_rewards/accuracies": 0.6399999856948853,
+      "eval_rewards/chosen": -0.0393824502825737,
+      "eval_rewards/margins": 0.026689546182751656,
+      "eval_rewards/rejected": -0.0660719946026802,
+      "eval_runtime": 65.4972,
+      "eval_samples_per_second": 11.985,
+      "eval_steps_per_second": 0.382,
+      "step": 200
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 38.64475256798845,
+      "learning_rate": 1.4303513272105055e-08,
+      "logits/chosen": -0.9661673307418823,
+      "logits/rejected": -1.5310702323913574,
+      "logps/chosen": -31.798084259033203,
+      "logps/rejected": -55.2061882019043,
+      "loss": 0.6543,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": 0.008609571494162083,
+      "rewards/margins": 0.0721936896443367,
+      "rewards/rejected": -0.06358411908149719,
+      "step": 210
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 46.11579146010557,
+      "learning_rate": 1.0087684049605349e-08,
+      "logits/chosen": -1.0623886585235596,
+      "logits/rejected": -1.484731912612915,
+      "logps/chosen": -33.05571365356445,
+      "logps/rejected": -68.4007568359375,
+      "loss": 0.6512,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.002279428532347083,
+      "rewards/margins": 0.09988276660442352,
+      "rewards/rejected": -0.09760333597660065,
+      "step": 220
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 42.366279277913364,
+      "learning_rate": 6.538031058667609e-09,
+      "logits/chosen": -0.9526311159133911,
+      "logits/rejected": -1.5703321695327759,
+      "logps/chosen": -32.05732727050781,
+      "logps/rejected": -69.91355895996094,
+      "loss": 0.6539,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -0.0006113927811384201,
+      "rewards/margins": 0.10779329389333725,
+      "rewards/rejected": -0.10840468108654022,
+      "step": 230
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 42.96686513067178,
+      "learning_rate": 3.713801536555483e-09,
+      "logits/chosen": -1.1161487102508545,
+      "logits/rejected": -1.5149171352386475,
+      "logps/chosen": -31.100393295288086,
+      "logps/rejected": -60.296607971191406,
+      "loss": 0.6558,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.0010345360497012734,
+      "rewards/margins": 0.09006427228450775,
+      "rewards/rejected": -0.09109880030155182,
+      "step": 240
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 46.95737595476474,
+      "learning_rate": 1.662134681666899e-09,
+      "logits/chosen": -0.9997628927230835,
+      "logits/rejected": -1.6180452108383179,
+      "logps/chosen": -27.377477645874023,
+      "logps/rejected": -54.080360412597656,
+      "loss": 0.6512,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 0.0026857522316277027,
+      "rewards/margins": 0.09887233376502991,
+      "rewards/rejected": -0.0961865708231926,
+      "step": 250
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 42.2077659611999,
+      "learning_rate": 4.172748534499448e-10,
+      "logits/chosen": -1.158440113067627,
+      "logits/rejected": -1.4339531660079956,
+      "logps/chosen": -32.833595275878906,
+      "logps/rejected": -55.285552978515625,
+      "loss": 0.6543,
+      "rewards/accuracies": 0.856249988079071,
+      "rewards/chosen": -0.0024300869554281235,
+      "rewards/margins": 0.09633214771747589,
+      "rewards/rejected": -0.09876222908496857,
+      "step": 260
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 44.84738059556724,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.0697628259658813,
+      "logits/rejected": -1.563280463218689,
+      "logps/chosen": -33.97581481933594,
+      "logps/rejected": -64.04183197021484,
+      "loss": 0.6482,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": -0.0003928671940229833,
+      "rewards/margins": 0.0867936760187149,
+      "rewards/rejected": -0.0871865525841713,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "step": 270,
+      "total_flos": 0.0,
+      "train_loss": 0.1692200431117305,
+      "train_runtime": 798.9647,
+      "train_samples_per_second": 21.608,
+      "train_steps_per_second": 0.338
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 270,
+  "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
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb8c8f3b2279a0d2587e5909f14850f67c4f2fb3847bbf21ea984a3226d14066
+oid sha256:0e423e6281d937957b182db4274e151dd830ea7f134ddb99760f67ce8bed87a0
 size 6200