botways/llama_cpo_finetune

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+model_name: llama-CPO
+tags:
+- generated_from_trainer
+- trl
+- cpo
+licence: license
+---
+
+# Model Card for llama-CPO
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="botways/llama-CPO", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with CPO, a method introduced in [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://huggingface.co/papers/2401.08417).
+
+### Framework versions
+
+- TRL: 0.12.1
+- Transformers: 4.46.3
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+Cite CPO as:
+
+```bibtex
+@inproceedings{xu2024contrastive,
+    title        = {{Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation}},
+    author       = {Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
+    year         = 2024,
+    booktitle    = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},
+    publisher    = {OpenReview.net},
+    url          = {https://openreview.net/forum?id=51iwkioZpn}
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582281102245dc527b595361d724185f2149e40472dc5f25be7b1f3e03a31ccb
+size 572574272

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 1.8173785209655762,
+      "learning_rate": 7.435897435897435e-07,
+      "logits/chosen": 0.13414913415908813,
+      "logits/rejected": 0.12645891308784485,
+      "logps/chosen": -298.76983642578125,
+      "logps/rejected": -261.02435302734375,
+      "loss": 9.7803,
+      "nll_loss": 1.0939728021621704,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -29.87698745727539,
+      "rewards/margins": -3.774548292160034,
+      "rewards/rejected": -26.102436065673828,
+      "step": 10
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.8889318704605103,
+      "learning_rate": 4.871794871794871e-07,
+      "logits/chosen": 0.077309250831604,
+      "logits/rejected": 0.12109130620956421,
+      "logps/chosen": -277.27899169921875,
+      "logps/rejected": -260.14141845703125,
+      "loss": 8.6446,
+      "nll_loss": 1.0915288925170898,
+      "rewards/accuracies": 0.4749999940395355,
+      "rewards/chosen": -27.7278995513916,
+      "rewards/margins": -1.7137558460235596,
+      "rewards/rejected": -26.014141082763672,
+      "step": 20
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 1.609092354774475,
+      "learning_rate": 2.3076923076923078e-07,
+      "logits/chosen": 0.09378460794687271,
+      "logits/rejected": 0.0867479220032692,
+      "logps/chosen": -280.64697265625,
+      "logps/rejected": -273.1399841308594,
+      "loss": 7.8556,
+      "nll_loss": 1.1089527606964111,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -28.064701080322266,
+      "rewards/margins": -0.7507012486457825,
+      "rewards/rejected": -27.31399917602539,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "step": 39,
+      "total_flos": 0.0,
+      "train_loss": 8.851261627979767,
+      "train_runtime": 435.0584,
+      "train_samples_per_second": 0.69,
+      "train_steps_per_second": 0.09
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5786356a82264536514208a1f3b3612cb7f48f7f87a70601536c758e745411
+size 5624