Training in progress, step 10

README.md

@@ -1,199 +1,141 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
+license: apache-2.0
+base_model: openai/gpt-oss-20b
+tags:
+- axolotl
+- base_model:adapter:openai/gpt-oss-20b
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: gpt-oss-20b-olympiads-malign-prompt-benign-answer-reasoning-4
+  results: []
 ---
 
-# Model Card for Model ID
+<!-- 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. -->
 
-<!-- Provide a quick summary of what the model is/does. -->
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
 
+axolotl version: `0.12.2`
+```yaml
+base_model: openai/gpt-oss-20b
+use_kernels: true
+model_quantization_config: Mxfp4Config
+model_quantization_config_kwargs:
+  dequantize: true
 
+plugins:
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
 
-## Model Details
+experimental_skip_move_to_device: true  # prevent OOM by not putting model to GPU before sharding
 
-### Model Description
+datasets:
+  - path: /workspace/swe-tests/scripts/1_low_stakes_control/sft/data/olympiads/gptoss20b/malign_prompt_benign_answers/train_reasoning_4.jsonl
+    ds_type: json
+    type: chat_template
+    field_thinking: thinking
+    template_thinking_key: thinking
+    split: train
 
-<!-- Provide a longer summary of what this model is. -->
+test_datasets:
+  - path: /workspace/swe-tests/scripts/1_low_stakes_control/sft/data/olympiads/gptoss20b/malign_prompt_benign_answers/val_reasoning_1.jsonl
+    ds_type: json
+    type: chat_template
+    field_thinking: thinking
+    template_thinking_key: thinking
+    split: train
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+output_dir: ./outputs/out/gpt-oss-20b-olympiads-malign-prompt-benign-answer-reasoning-4
 
-- **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]
+sequence_len: 4096
+#sample_packing: true
 
-### Model Sources [optional]
+adapter: lora
+lora_r: 32
+lora_alpha: 32
+lora_dropout: 0.0  # dropout not supported when using LoRA over expert parameters
+lora_target_linear: true
 
-<!-- Provide the basic links for the model. -->
+# TODO: not supported for now, see peft#2710xw
+#lora_target_parameters:  # target the experts in the last two layers
+#  - "22._checkpoint_wrapped_module.mlp.experts.gate_up_proj"
+#  - "22._checkpoint_wrapped_module.mlp.experts.down_proj"
+#  - "23._checkpoint_wrapped_module.mlp.experts.gate_up_proj"
+#  - "23._checkpoint_wrapped_module.mlp.experts.down_proj"
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+wandb_project: low-stakes-control-sft
+wandb_entity: mats-low-stakes
+wandb_name: gpt-oss-20b-olympiads-malign-prompt-benign-answer-reasoning-4
+wandb_log_model: checkpoint
+hub_model_id: EmilRyd/gpt-oss-20b-olympiads-malign-prompt-benign-answer-reasoning-4
 
-## Uses
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 70
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+optimizer: adamw_torch_8bit
+lr_scheduler: constant_with_warmup
+learning_rate: 1e-5
 
-### Direct Use
+bf16: true
+tf32: true
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+flash_attention: true
+attn_implementation: kernels-community/vllm-flash-attn3
 
-[More Information Needed]
+gradient_checkpointing: true
+activation_offloading: true
 
-### Downstream Use [optional]
+logging_steps: 1
+save_steps: 10
+save_only_model: true
+warmup_ratio: 0.01
+eval_steps: 10
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+special_tokens:
+eot_tokens:
+  - "<|end|>"
+```
 
-[More Information Needed]
+</details><br>
 
-### Out-of-Scope Use
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mats-low-stakes/low-stakes-control-sft/runs/adyl6zpv)
+# gpt-oss-20b-olympiads-malign-prompt-benign-answer-reasoning-4
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) on an unknown dataset.
 
-[More Information Needed]
+## Model description
 
-## Bias, Risks, and Limitations
+More information needed
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+## Intended uses & limitations
 
-[More Information Needed]
+More information needed
 
-### Recommendations
+## Training and evaluation data
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+More information needed
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+## Training procedure
 
-## How to Get Started with the Model
+### Training hyperparameters
 
-Use the code below to get started with the model.
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use adamw_torch_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant_with_warmup
+- training_steps: 70
 
-[More Information Needed]
+### Framework versions
 
-## 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]
+- PEFT 0.17.0
+- Transformers 4.55.2
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai/gpt-oss-20b",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8075eada8d4860c99ed0016fa478273ab0d5f57307dd4117545d422566527d0a
+size 63726760

config.json

@@ -63,6 +63,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.55.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 201088
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7d3ca9d685edeac76468e5505ce14e13423fd3480ba668c890654f6374063c2
+size 6968