Training in progress, step 100

README.md

@@ -74,7 +74,7 @@ hub_model_id: EmilRyd/gpt-oss-20b-olympiads-sonnet-45-malign-prompt-benign-answe
 
 gradient_accumulation_steps: 2
 micro_batch_size: 5
-num_epochs: 50
+num_epochs: 100
 
 optimizer: adamw_torch_8bit
 lr_scheduler: constant_with_warmup
@@ -102,7 +102,7 @@ eot_tokens:
 
 </details><br>
 
-[<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/858al04y)
+[<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/edfzbi74)
 # gpt-oss-20b-olympiads-sonnet-45-malign-prompt-benign-answer-reasoning-10
 
 This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) on an unknown dataset.
@@ -132,7 +132,8 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 10
 - 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: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 100
 
 ### Framework versions
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27a7b0a66dd77c7d70fd474b731cde549aa25736f2a17804e81e98d7ccb2eb1
+oid sha256:99e8ca2c14010ffec0018624c5a084be7c11897bac0e81e8d10e8a30deeaf757
 size 63726760