Upload folder using huggingface_hub

README.md

@@ -0,0 +1,73 @@
+---
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+library_name: peft
+model_name: out_dpo
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-360M-Instruct
+- dpo
+- lora
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for out_dpo
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct).
+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="None", 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 DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- PEFT 0.20.0
+- TRL: 1.7.1
+- Transformers: 5.16.1
+- Pytorch: 2.11.0+cu128
+- Datasets: 5.0.1
+- Tokenizers: 0.23.1
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a35c6e17b374794dbe53dea3228d6711883c462a170b9aeed823e1da7e0ad5
+size 3293480

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-5/README.md

@@ -0,0 +1,209 @@
+---
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-360M-Instruct
+- dpo
+- lora
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

checkpoint-5/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a35c6e17b374794dbe53dea3228d6711883c462a170b9aeed823e1da7e0ad5
+size 3293480

checkpoint-5/chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b54be39162bc90c6ed57e85b5ac6e053dc2c3f4023c998f2490f6d58f929df7
+size 6661707

checkpoint-5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45166ae03051a68ef058e9ed1d9918787ca21ad038be4d1bdc35ef2bf3e09921
+size 14645

checkpoint-5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc0694ce15b957c118c95c4d8af3aa9c5fa70bea18680bf07ee1c8844e5fb2d
+size 1465

checkpoint-5/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-5/trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.05056069791317,
+      "epoch": 0.2,
+      "grad_norm": 3.576743949906813e-07,
+      "learning_rate": 0.0,
+      "logits/chosen": -1.970146747398138,
+      "logits/rejected": -1.970146747398138,
+      "logps/chosen": -18.030120849609375,
+      "logps/rejected": -18.030120849609375,
+      "loss": 0.6931471824645996,
+      "mean_token_accuracy": 0.8783265054225922,
+      "num_tokens": 2172.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.8472362160682678,
+      "epoch": 0.4,
+      "grad_norm": 3.372371963905607e-07,
+      "learning_rate": 1e-07,
+      "logits/chosen": -1.6947472581937175,
+      "logits/rejected": -1.6947472581937175,
+      "logps/chosen": -29.89427399635315,
+      "logps/rejected": -29.89427399635315,
+      "loss": 0.6931471824645996,
+      "mean_token_accuracy": 0.7170108556747437,
+      "num_tokens": 4280.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "entropy": 1.994214117527008,
+      "epoch": 0.6,
+      "grad_norm": 3.646446486982313e-07,
+      "learning_rate": 2e-07,
+      "logits/chosen": -2.1313482575829665,
+      "logits/rejected": -2.1313482575829665,
+      "logps/chosen": -12.822995781898499,
+      "logps/rejected": -12.822995781898499,
+      "loss": 0.6931471824645996,
+      "mean_token_accuracy": 0.8758726269006729,
+      "num_tokens": 6450.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 3
+    },
+    {
+      "entropy": 2.7409143149852753,
+      "epoch": 0.8,
+      "grad_norm": 2.2604422156291548e-07,
+      "learning_rate": 3e-07,
+      "logits/chosen": -3.046862468220829,
+      "logits/rejected": -3.046862468220829,
+      "logps/chosen": -16.68446946144104,
+      "logps/rejected": -16.68446946144104,
+      "loss": 0.6931471824645996,
+      "mean_token_accuracy": 0.6849128678441048,
+      "num_tokens": 8154.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 4
+    },
+    {
+      "entropy": 1.3964595794677734,
+      "epoch": 1.0,
+      "grad_norm": 4.3739885313698323e-07,
+      "learning_rate": 4e-07,
+      "logits/chosen": -2.213178881348543,
+      "logits/rejected": -2.213178881348543,
+      "logps/chosen": -44.113500118255615,
+      "logps/rejected": -44.1134991645813,
+      "loss": 0.6931471824645996,
+      "mean_token_accuracy": 0.7640228718519211,
+      "num_tokens": 10660.0,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0009971618565032259,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0009971618565032259,
+      "step": 5
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 6230855308800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5222b4de83f63eaf6e8119ce1e054c34d2f3447d2e9eada52d9ae1668f2b99d3
+size 5841

dpo_config.yaml

@@ -0,0 +1,143 @@
+accelerator_config:
+  dispatch_batches: null
+  even_batches: true
+  gradient_accumulation_kwargs: null
+  non_blocking: false
+  split_batches: false
+  use_seedable_sampler: true
+activation_offloading: false
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+auto_find_batch_size: false
+average_tokens_across_devices: true
+batch_eval_metrics: false
+beta: 0.1
+bf16: true
+bf16_full_eval: false
+data_seed: 42
+dataloader_drop_last: false
+dataloader_in_order: true
+dataloader_multiprocessing_context: null
+dataloader_num_workers: 0
+dataloader_persistent_workers: false
+dataloader_pin_memory: true
+dataloader_prefetch_factor: null
+dataset_num_proc: null
+ddp_backend: null
+ddp_broadcast_buffers: null
+ddp_bucket_cap_mb: null
+ddp_find_unused_parameters: null
+ddp_static_graph: null
+ddp_timeout: 1800
+debug: []
+deepspeed: null
+disable_dropout: true
+disable_tqdm: false
+discopop_tau: 0.05
+do_eval: false
+do_predict: false
+do_train: false
+enable_jit_checkpoint: false
+eval_accumulation_steps: null
+eval_delay: 0
+eval_do_concat_batches: true
+eval_on_start: false
+eval_steps: null
+eval_strategy: 'no'
+eval_use_gather_object: false
+f_alpha_divergence_coef: 0.5
+f_divergence_type: reverse_kl
+fp16: false
+fp16_full_eval: false
+fsdp: null
+fsdp_config: null
+full_determinism: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+gradient_checkpointing_kwargs: null
+greater_is_better: null
+hub_always_push: false
+hub_model_id: null
+hub_private_repo: null
+hub_revision: null
+hub_strategy: every_save
+hub_token: <HUB_TOKEN>
+ignore_data_skip: false
+include_for_metrics: []
+include_num_input_tokens_seen: 'no'
+label_names: null
+label_smoothing: 0.0
+label_smoothing_factor: 0.0
+ld_alpha: null
+learning_rate: 1.0e-06
+length_column_name: length
+liger_kernel_config: null
+load_best_model_at_end: false
+local_rank: -1
+log_level: passive
+log_level_replica: warning
+log_on_each_node: true
+logging_first_step: false
+logging_nan_inf_filter: true
+logging_steps: 1
+logging_strategy: steps
+loss_type:
+- sigmoid
+loss_weights: null
+lr_scheduler_kwargs: null
+lr_scheduler_type: linear
+max_grad_norm: 1.0
+max_length: 1024
+max_steps: -1
+metric_for_best_model: null
+model_init_kwargs: null
+neftune_noise_alpha: null
+num_train_epochs: 1
+optim: adamw_torch
+optim_args: null
+optim_target_modules: null
+output_dir: ./out_dpo
+pad_to_multiple_of: null
+pad_token: <PAD_TOKEN>
+padding_free: false
+parallelism_config: null
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 2
+precompute_ref_batch_size: null
+precompute_ref_log_probs: false
+prediction_loss_only: false
+project: huggingface
+push_to_hub: false
+ref_model_mixup_alpha: 0.6
+ref_model_sync_steps: 512
+remove_unused_columns: false
+report_to: []
+restore_callback_states_from_checkpoint: false
+resume_from_checkpoint: null
+run_name: null
+save_on_each_node: false
+save_only_model: false
+save_steps: 500
+save_strategy: steps
+save_total_limit: null
+seed: 42
+skip_memory_metrics: true
+sync_ref_model: false
+tf32: null
+torch_compile: false
+torch_compile_backend: null
+torch_compile_mode: null
+torch_empty_cache_steps: null
+trackio_bucket_id: null
+trackio_space_id: null
+trackio_static_space_id: null
+train_sampling_strategy: random
+truncation_mode: keep_start
+trust_remote_code: false
+use_cache: false
+use_cpu: false
+use_liger_kernel: false
+use_weighting: false
+warmup_steps: 10
+weight_decay: 0.0

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5222b4de83f63eaf6e8119ce1e054c34d2f3447d2e9eada52d9ae1668f2b99d3
+size 5841

training_stats.json

@@ -0,0 +1,83 @@
+{
+  "model": "HuggingFaceTB/SmolLM2-360M-Instruct",
+  "dataset_name": "unknown",
+  "output_dir": "./out_dpo",
+  "use_rollouts": true,
+  "agentic_mode": true,
+  "tools": [
+    "query_inventory"
+  ],
+  "train_size": 40,
+  "eval_size": 0,
+  "final_loss": 0.6931471824645996,
+  "total_steps": 5,
+  "training_history": [],
+  "metrics": {
+    "train_runtime": 184.4542,
+    "train_samples_per_second": 0.217,
+    "train_steps_per_second": 0.027,
+    "total_flos": 6230855308800.0,
+    "train_loss": 0.6931471824645996,
+    "epoch": 1.0
+  },
+  "config_kwargs": {
+    "model": "HuggingFaceTB/SmolLM2-360M-Instruct",
+    "dataset_config": null,
+    "split": "train",
+    "max_samples": 40,
+    "column_mapping": null,
+    "system_prompt": "You are the Dallas DC planner. Call query_inventory with a read-only SQL SELECT against customers, orders, order_lines, inventory. Join when a ticket names a customer or order id. After the tool returns, reply with the numeric answer only.",
+    "enable_thinking": false,
+    "reward_funcs": "<callable: combined_reward(reward_tool_used+reward_correct_answer)>",
+    "tools": [
+      "<function query_inventory at 0x7f35c5b43100>"
+    ],
+    "rollout_backend": null,
+    "max_steps_per_turn": 8,
+    "engine_kwargs": {},
+    "peft_config": {
+      "r": 8,
+      "lora_alpha": 16,
+      "lora_dropout": 0.0,
+      "bias": "none",
+      "task_type": "CAUSAL_LM"
+    },
+    "output_dir": "./out_dpo",
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 2,
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 1e-06,
+    "warmup_ratio": 0.03,
+    "warmup_steps": 10,
+    "weight_decay": 0.0,
+    "lr_scheduler_type": "linear",
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "data_seed": 42,
+    "optim": "adamw_torch",
+    "num_generations": 2,
+    "max_prompt_length": 256,
+    "max_completion_length": 128,
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "beta": 0.1,
+    "use_vllm": false,
+    "vllm_mode": "colocate",
+    "log_completions": true,
+    "chat_template_kwargs": {
+      "enable_thinking": false
+    },
+    "logging_steps": 1,
+    "save_steps": 500,
+    "eval_strategy": "no",
+    "report_to": "none",
+    "push_to_hub": false,
+    "bf16": true,
+    "fp16": false,
+    "gradient_checkpointing": true,
+    "dataloader_num_workers": 0,
+    "remove_unused_columns": false,
+    "use_rollouts": true,
+    "train_dataset": "Dataset({\n    features: ['prompt', 'answer'],\n    num_rows: 40\n})"
+  }
+}