Instructions to use AiAF/rp-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AiAF/rp-2b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b-it")
model = PeftModel.from_pretrained(base_model, "AiAF/rp-2b")

Transformers

How to use AiAF/rp-2b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AiAF/rp-2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AiAF/rp-2b")
model = AutoModelForCausalLM.from_pretrained("AiAF/rp-2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AiAF/rp-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AiAF/rp-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AiAF/rp-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AiAF/rp-2b

SGLang

How to use AiAF/rp-2b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AiAF/rp-2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AiAF/rp-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AiAF/rp-2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AiAF/rp-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AiAF/rp-2b with Docker Model Runner:
```
docker model run hf.co/AiAF/rp-2b
```

AiAF commited on Mar 30

Commit

7e5d2d6

verified ·

1 Parent(s): ef695d7

Training in progress, step 800

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
debug.log +105 -1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f145aad3e393aacb1ea6687fe5c794bd1505c6b68c50e5038c6eac34efa7e4d6
 size 102264160

 version https://git-lfs.github.com/spec/v1
+oid sha256:cd804fe5a6a07ca92c0d9df3ee8901a99a952af466c85b5d67804f3b9b5754fc
 size 102264160

debug.log CHANGED Viewed

@@ -1908,4 +1908,108 @@ trainable params: 25,559,040 || all params: 2,639,900,928 || trainable%: 0.9682
 75%|▊| 751/1000 [12:59<13:40,  3.29s/it]
 75%|▊| 752/1000 [12:59<10:27,  2.53s/it]
 75%|▊| 752/1000 [12:59<10:27,  2.53s/it]
 75%|▊| 753/1000 [13:00<08:14,  2.00s/it]
 75%|▊| 753/1000 [13:00<08:14,  2.00s/it]
 75%|▊| 754/1000 [13:01<06:34,  1.60s/it]
 75%|▊| 754/1000 [13:01<06:34,  1.60s/it]
 75%|▊| 754/1000 [13:01<06:34,  1.60s/it]
 76%|▊| 755/1000 [13:01<05:24,  1.33s/it]
 76%|▊| 755/1000 [13:01<05:24,  1.33s/it]
 76%|▊| 756/1000 [13:02<04:42,  1.16s/it]
 76%|▊| 756/1000 [13:02<04:42,  1.16s/it]
 76%|▊| 757/1000 [13:03<04:11,  1.04s/it]
 76%|▊| 757/1000 [13:03<04:11,  1.04s/it]
 76%|▊| 758/1000 [13:04<03:48,  1.06it/s]
 76%|▊| 758/1000 [13:04<03:48,  1.06it/s]
 76%|▊| 759/1000 [13:04<03:31,  1.14it/s]
 76%|▊| 759/1000 [13:04<03:31,  1.14it/s]
 76%|▊| 760/1000 [13:05<03:21,  1.19it/s]
 76%|▊| 760/1000 [13:05<03:21,  1.19it/s]
 76%|▊| 761/1000 [13:06<03:17,  1.21it/s]
 76%|▊| 761/1000 [13:06<03:17,  1.21it/s]
 76%|▊| 762/1000 [13:07<03:08,  1.26it/s]
 76%|▊| 762/1000 [13:07<03:08,  1.26it/s]
 76%|▊| 763/1000 [13:07<03:05,  1.28it/s]
 76%|▊| 763/1000 [13:07<03:05,  1.28it/s]
 76%|▊| 764/1000 [13:08<03:03,  1.28it/s]
 76%|▊| 764/1000 [13:08<03:03,  1.28it/s]
 76%|▊| 765/1000 [13:09<03:01,  1.29it/s]
 76%|▊| 765/1000 [13:09<03:01,  1.29it/s]
 77%|▊| 766/1000 [13:10<03:01,  1.29it/s]
 77%|▊| 766/1000 [13:10<03:01,  1.29it/s]
 77%|▊| 767/1000 [13:10<02:56,  1.32it/s]
 77%|▊| 767/1000 [13:10<02:56,  1.32it/s]
 77%|▊| 768/1000 [13:11<02:55,  1.32it/s]
 77%|▊| 768/1000 [13:11<02:55,  1.32it/s]
 77%|▊| 769/1000 [13:12<02:53,  1.33it/s]
 77%|▊| 769/1000 [13:12<02:53,  1.33it/s]
 77%|▊| 770/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 770/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 771/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 771/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 772/1000 [13:14<02:52,  1.32it/s]
 77%|▊| 772/1000 [13:14<02:52,  1.32it/s]
 77%|▊| 773/1000 [13:15<02:50,  1.33it/s]
 77%|▊| 773/1000 [13:15<02:50,  1.33it/s]
 77%|▊| 774/1000 [13:16<02:49,  1.33it/s]
 77%|▊| 774/1000 [13:16<02:49,  1.33it/s]
 78%|▊| 775/1000 [13:16<02:46,  1.35it/s]
 78%|▊| 775/1000 [13:16<02:46,  1.35it/s]
 78%|▊| 776/1000 [13:17<02:45,  1.36it/s]
 78%|▊| 776/1000 [13:17<02:45,  1.36it/s]
 78%|▊| 777/1000 [13:18<02:45,  1.34it/s]
 78%|▊| 777/1000 [13:18<02:45,  1.34it/s]
 78%|▊| 778/1000 [13:19<02:45,  1.34it/s]
 78%|▊| 778/1000 [13:19<02:45,  1.34it/s]
 78%|▊| 779/1000 [13:19<02:47,  1.32it/s]
 78%|▊| 779/1000 [13:19<02:47,  1.32it/s]
 78%|▊| 780/1000 [13:20<02:46,  1.33it/s]
 78%|▊| 780/1000 [13:20<02:46,  1.33it/s]
 78%|▊| 781/1000 [13:21<02:43,  1.34it/s]
 78%|▊| 781/1000 [13:21<02:43,  1.34it/s]
 78%|▊| 782/1000 [13:22<02:40,  1.36it/s]
 78%|▊| 782/1000 [13:22<02:40,  1.36it/s]
 78%|▊| 783/1000 [13:22<02:41,  1.34it/s]
 78%|▊| 783/1000 [13:22<02:41,  1.34it/s]
 78%|▊| 784/1000 [13:23<02:40,  1.35it/s]
 78%|▊| 784/1000 [13:23<02:40,  1.35it/s]
 78%|▊| 785/1000 [13:24<02:40,  1.34it/s]
 78%|▊| 785/1000 [13:24<02:40,  1.34it/s]
 79%|▊| 786/1000 [13:25<02:37,  1.36it/s]
 79%|▊| 786/1000 [13:25<02:37,  1.36it/s]
 79%|▊| 787/1000 [13:25<02:39,  1.34it/s]
 79%|▊| 787/1000 [13:25<02:39,  1.34it/s]
 79%|▊| 788/1000 [13:26<02:36,  1.35it/s]
 79%|▊| 788/1000 [13:26<02:36,  1.35it/s]
 79%|▊| 789/1000 [13:27<02:35,  1.36it/s]
 79%|▊| 789/1000 [13:27<02:35,  1.36it/s]
 79%|▊| 790/1000 [13:28<02:38,  1.33it/s]
 79%|▊| 790/1000 [13:28<02:38,  1.33it/s]
 79%|▊| 791/1000 [13:28<02:33,  1.36it/s]
 79%|▊| 791/1000 [13:28<02:33,  1.36it/s]
 79%|▊| 792/1000 [13:29<02:33,  1.35it/s]
 79%|▊| 792/1000 [13:29<02:33,  1.35it/s]
 79%|▊| 793/1000 [13:30<02:31,  1.36it/s]
 79%|▊| 793/1000 [13:30<02:31,  1.36it/s]
 79%|▊| 794/1000 [13:31<02:31,  1.36it/s]
 79%|▊| 794/1000 [13:31<02:31,  1.36it/s]
 80%|▊| 795/1000 [13:31<02:31,  1.36it/s]
 80%|▊| 795/1000 [13:31<02:31,  1.36it/s]
 80%|▊| 796/1000 [13:32<02:30,  1.36it/s]
 80%|▊| 796/1000 [13:32<02:30,  1.36it/s]
 80%|▊| 797/1000 [13:33<02:30,  1.35it/s]
 80%|▊| 797/1000 [13:33<02:30,  1.35it/s]
 80%|▊| 798/1000 [13:33<02:29,  1.35it/s]
 80%|▊| 798/1000 [13:33<02:29,  1.35it/s]
 80%|▊| 799/1000 [13:34<02:30,  1.33it/s]
 80%|▊| 799/1000 [13:34<02:30,  1.33it/s]
 80%|▊| 800/1000 [13:35<02:28,  1.34it/s]
 80%|▊| 800/1000 [13:35<02:28,  1.34it/s][2026-03-30 14:48:49,462] [INFO] [axolotl.core.trainers.base.evaluate:401] [PID:37135] Running evaluation step...
  0%|            | 0/100 [00:00<?, ?it/s][A
  3%|    | 3/100 [00:00<00:05, 18.22it/s][A
  5%|▏   | 5/100 [00:00<00:05, 15.88it/s][A
  7%|▎   | 7/100 [00:00<00:05, 16.81it/s][A
  9%|▎   | 9/100 [00:00<00:05, 15.81it/s][A
 11%|▎  | 11/100 [00:00<00:05, 16.34it/s][A
 13%|▍  | 13/100 [00:00<00:05, 16.63it/s][A
 15%|▍  | 15/100 [00:00<00:04, 17.30it/s][A
 17%|▌  | 17/100 [00:01<00:04, 16.87it/s][A
 19%|▌  | 19/100 [00:01<00:04, 17.69it/s][A
 21%|▋  | 21/100 [00:01<00:04, 16.98it/s][A
 23%|▋  | 23/100 [00:01<00:04, 17.49it/s][A
 25%|▊  | 25/100 [00:01<00:04, 17.09it/s][A
 27%|▊  | 27/100 [00:01<00:04, 17.18it/s][A
 29%|▊  | 29/100 [00:01<00:04, 16.48it/s][A
 31%|▉  | 31/100 [00:01<00:04, 17.11it/s][A
 33%|▉  | 33/100 [00:01<00:04, 16.51it/s][A
 36%|█  | 36/100 [00:02<00:03, 17.86it/s][A
 38%|█▏ | 38/100 [00:02<00:03, 17.47it/s][A
 40%|█▏ | 40/100 [00:02<00:03, 17.54it/s][A
 42%|█▎ | 42/100 [00:02<00:03, 18.02it/s][A
 44%|█▎ | 44/100 [00:02<00:03, 17.95it/s][A
 46%|█▍ | 46/100 [00:02<00:03, 14.58it/s][A
 48%|█▍ | 48/100 [00:02<00:03, 15.62it/s][A
 50%|█▌ | 50/100 [00:02<00:03, 15.61it/s][A
 52%|█▌ | 52/100 [00:03<00:03, 15.99it/s][A
 54%|█▌ | 54/100 [00:03<00:02, 15.68it/s][A
 56%|█▋ | 56/100 [00:03<00:02, 16.17it/s][A
 58%|█▋ | 58/100 [00:03<00:02, 16.20it/s][A
 60%|█▊ | 60/100 [00:03<00:02, 16.75it/s][A
 62%|█▊ | 62/100 [00:03<00:02, 17.22it/s][A
 64%|█▉ | 64/100 [00:03<00:02, 17.50it/s][A
 66%|█▉ | 66/100 [00:03<00:02, 16.78it/s][A
 68%|██ | 68/100 [00:04<00:01, 17.35it/s][A
 70%|██ | 70/100 [00:04<00:01, 16.79it/s][A
 72%|██▏| 72/100 [00:04<00:01, 17.31it/s][A
 74%|██▏| 74/100 [00:04<00:01, 16.43it/s][A
 77%|██▎| 77/100 [00:04<00:01, 17.05it/s][A
 79%|██▎| 79/100 [00:04<00:01, 17.48it/s][A
 81%|██▍| 81/100 [00:04<00:01, 17.23it/s][A
 84%|██▌| 84/100 [00:04<00:00, 18.43it/s][A
 86%|██▌| 86/100 [00:05<00:00, 17.73it/s][A
 89%|██▋| 89/100 [00:05<00:00, 17.95it/s][A
 91%|██▋| 91/100 [00:05<00:00, 18.29it/s][A
 93%|██▊| 93/100 [00:05<00:00, 17.19it/s][A
 95%|██▊| 95/100 [00:05<00:00, 16.82it/s][A
 97%|██▉| 97/100 [00:05<00:00, 16.89it/s][A
 80%|▊| 800/1000 [13:41<02:28,  1.34it/s]
                                         [A[2026-03-30 14:48:55,637] [INFO] [axolotl.core.trainers.base._save:722] [PID:37135] Saving model checkpoint to /workspace/data/axolotl-outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-800
 80%|▊| 801/1000 [13:44<10:45,  3.25s/it]
 80%|▊| 801/1000 [13:44<10:45,  3.25s/it]
 80%|▊| 802/1000 [13:45<08:15,  2.50s/it]
 80%|▊| 802/1000 [13:45<08:15,  2.50s/it]
 80%|▊| 803/1000 [13:46<06:28,  1.97s/it]
 80%|▊| 803/1000 [13:46<06:28,  1.97s/it]
 80%|▊| 804/1000 [13:46<05:12,  1.59s/it]
 80%|▊| 804/1000 [13:46<05:12,  1.59s/it]

 75%|▊| 751/1000 [12:59<13:40,  3.29s/it]
 75%|▊| 752/1000 [12:59<10:27,  2.53s/it]
 75%|▊| 752/1000 [12:59<10:27,  2.53s/it]
 75%|▊| 753/1000 [13:00<08:14,  2.00s/it]
 75%|▊| 753/1000 [13:00<08:14,  2.00s/it]
 75%|▊| 754/1000 [13:01<06:34,  1.60s/it]
 75%|▊| 754/1000 [13:01<06:34,  1.60s/it]
 75%|▊| 754/1000 [13:01<06:34,  1.60s/it]
 76%|▊| 755/1000 [13:01<05:24,  1.33s/it]
 76%|▊| 755/1000 [13:01<05:24,  1.33s/it]
 76%|▊| 756/1000 [13:02<04:42,  1.16s/it]
 76%|▊| 756/1000 [13:02<04:42,  1.16s/it]
 76%|▊| 757/1000 [13:03<04:11,  1.04s/it]
 76%|▊| 757/1000 [13:03<04:11,  1.04s/it]
 76%|▊| 758/1000 [13:04<03:48,  1.06it/s]
 76%|▊| 758/1000 [13:04<03:48,  1.06it/s]
 76%|▊| 759/1000 [13:04<03:31,  1.14it/s]
 76%|▊| 759/1000 [13:04<03:31,  1.14it/s]
 76%|▊| 760/1000 [13:05<03:21,  1.19it/s]
 76%|▊| 760/1000 [13:05<03:21,  1.19it/s]
 76%|▊| 761/1000 [13:06<03:17,  1.21it/s]
 76%|▊| 761/1000 [13:06<03:17,  1.21it/s]
 76%|▊| 762/1000 [13:07<03:08,  1.26it/s]
 76%|▊| 762/1000 [13:07<03:08,  1.26it/s]
 76%|▊| 763/1000 [13:07<03:05,  1.28it/s]
 76%|▊| 763/1000 [13:07<03:05,  1.28it/s]
 76%|▊| 764/1000 [13:08<03:03,  1.28it/s]
 76%|▊| 764/1000 [13:08<03:03,  1.28it/s]
 76%|▊| 765/1000 [13:09<03:01,  1.29it/s]
 76%|▊| 765/1000 [13:09<03:01,  1.29it/s]
 77%|▊| 766/1000 [13:10<03:01,  1.29it/s]
 77%|▊| 766/1000 [13:10<03:01,  1.29it/s]
 77%|▊| 767/1000 [13:10<02:56,  1.32it/s]
 77%|▊| 767/1000 [13:10<02:56,  1.32it/s]
 77%|▊| 768/1000 [13:11<02:55,  1.32it/s]
 77%|▊| 768/1000 [13:11<02:55,  1.32it/s]
 77%|▊| 769/1000 [13:12<02:53,  1.33it/s]
 77%|▊| 769/1000 [13:12<02:53,  1.33it/s]
 77%|▊| 770/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 770/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 771/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 771/1000 [13:13<02:55,  1.31it/s]
 77%|▊| 772/1000 [13:14<02:52,  1.32it/s]
 77%|▊| 772/1000 [13:14<02:52,  1.32it/s]
 77%|▊| 773/1000 [13:15<02:50,  1.33it/s]
 77%|▊| 773/1000 [13:15<02:50,  1.33it/s]
 77%|▊| 774/1000 [13:16<02:49,  1.33it/s]
 77%|▊| 774/1000 [13:16<02:49,  1.33it/s]
 78%|▊| 775/1000 [13:16<02:46,  1.35it/s]
 78%|▊| 775/1000 [13:16<02:46,  1.35it/s]
 78%|▊| 776/1000 [13:17<02:45,  1.36it/s]
 78%|▊| 776/1000 [13:17<02:45,  1.36it/s]
 78%|▊| 777/1000 [13:18<02:45,  1.34it/s]
 78%|▊| 777/1000 [13:18<02:45,  1.34it/s]
 78%|▊| 778/1000 [13:19<02:45,  1.34it/s]
 78%|▊| 778/1000 [13:19<02:45,  1.34it/s]
 78%|▊| 779/1000 [13:19<02:47,  1.32it/s]
 78%|▊| 779/1000 [13:19<02:47,  1.32it/s]
 78%|▊| 780/1000 [13:20<02:46,  1.33it/s]
 78%|▊| 780/1000 [13:20<02:46,  1.33it/s]
 78%|▊| 781/1000 [13:21<02:43,  1.34it/s]
 78%|▊| 781/1000 [13:21<02:43,  1.34it/s]
 78%|▊| 782/1000 [13:22<02:40,  1.36it/s]
 78%|▊| 782/1000 [13:22<02:40,  1.36it/s]
 78%|▊| 783/1000 [13:22<02:41,  1.34it/s]
 78%|▊| 783/1000 [13:22<02:41,  1.34it/s]
 78%|▊| 784/1000 [13:23<02:40,  1.35it/s]
 78%|▊| 784/1000 [13:23<02:40,  1.35it/s]
 78%|▊| 785/1000 [13:24<02:40,  1.34it/s]
 78%|▊| 785/1000 [13:24<02:40,  1.34it/s]
 79%|▊| 786/1000 [13:25<02:37,  1.36it/s]
 79%|▊| 786/1000 [13:25<02:37,  1.36it/s]
 79%|▊| 787/1000 [13:25<02:39,  1.34it/s]
 79%|▊| 787/1000 [13:25<02:39,  1.34it/s]
 79%|▊| 788/1000 [13:26<02:36,  1.35it/s]
 79%|▊| 788/1000 [13:26<02:36,  1.35it/s]
 79%|▊| 789/1000 [13:27<02:35,  1.36it/s]
 79%|▊| 789/1000 [13:27<02:35,  1.36it/s]
 79%|▊| 790/1000 [13:28<02:38,  1.33it/s]
 79%|▊| 790/1000 [13:28<02:38,  1.33it/s]
 79%|▊| 791/1000 [13:28<02:33,  1.36it/s]
 79%|▊| 791/1000 [13:28<02:33,  1.36it/s]
 79%|▊| 792/1000 [13:29<02:33,  1.35it/s]
 79%|▊| 792/1000 [13:29<02:33,  1.35it/s]
 79%|▊| 793/1000 [13:30<02:31,  1.36it/s]
 79%|▊| 793/1000 [13:30<02:31,  1.36it/s]
 79%|▊| 794/1000 [13:31<02:31,  1.36it/s]
 79%|▊| 794/1000 [13:31<02:31,  1.36it/s]
 80%|▊| 795/1000 [13:31<02:31,  1.36it/s]
 80%|▊| 795/1000 [13:31<02:31,  1.36it/s]
 80%|▊| 796/1000 [13:32<02:30,  1.36it/s]
 80%|▊| 796/1000 [13:32<02:30,  1.36it/s]
 80%|▊| 797/1000 [13:33<02:30,  1.35it/s]
 80%|▊| 797/1000 [13:33<02:30,  1.35it/s]
 80%|▊| 798/1000 [13:33<02:29,  1.35it/s]
 80%|▊| 798/1000 [13:33<02:29,  1.35it/s]
 80%|▊| 799/1000 [13:34<02:30,  1.33it/s]
 80%|▊| 799/1000 [13:34<02:30,  1.33it/s]
 80%|▊| 800/1000 [13:35<02:28,  1.34it/s]
 80%|▊| 800/1000 [13:35<02:28,  1.34it/s][2026-03-30 14:48:49,462] [INFO] [axolotl.core.trainers.base.evaluate:401] [PID:37135] Running evaluation step...
  0%|            | 0/100 [00:00<?, ?it/s][A
  3%|    | 3/100 [00:00<00:05, 18.22it/s][A
  5%|▏   | 5/100 [00:00<00:05, 15.88it/s][A
  7%|▎   | 7/100 [00:00<00:05, 16.81it/s][A
  9%|▎   | 9/100 [00:00<00:05, 15.81it/s][A
 11%|▎  | 11/100 [00:00<00:05, 16.34it/s][A
 13%|▍  | 13/100 [00:00<00:05, 16.63it/s][A
 15%|▍  | 15/100 [00:00<00:04, 17.30it/s][A
 17%|▌  | 17/100 [00:01<00:04, 16.87it/s][A
 19%|▌  | 19/100 [00:01<00:04, 17.69it/s][A
 21%|▋  | 21/100 [00:01<00:04, 16.98it/s][A
 23%|▋  | 23/100 [00:01<00:04, 17.49it/s][A
 25%|▊  | 25/100 [00:01<00:04, 17.09it/s][A
 27%|▊  | 27/100 [00:01<00:04, 17.18it/s][A
 29%|▊  | 29/100 [00:01<00:04, 16.48it/s][A
 31%|▉  | 31/100 [00:01<00:04, 17.11it/s][A
 33%|▉  | 33/100 [00:01<00:04, 16.51it/s][A
 36%|█  | 36/100 [00:02<00:03, 17.86it/s][A
 38%|█▏ | 38/100 [00:02<00:03, 17.47it/s][A
 40%|█▏ | 40/100 [00:02<00:03, 17.54it/s][A
 42%|█▎ | 42/100 [00:02<00:03, 18.02it/s][A
 44%|█▎ | 44/100 [00:02<00:03, 17.95it/s][A
 46%|█▍ | 46/100 [00:02<00:03, 14.58it/s][A
 48%|█▍ | 48/100 [00:02<00:03, 15.62it/s][A
 50%|█▌ | 50/100 [00:02<00:03, 15.61it/s][A
 52%|█▌ | 52/100 [00:03<00:03, 15.99it/s][A
 54%|█▌ | 54/100 [00:03<00:02, 15.68it/s][A
 56%|█▋ | 56/100 [00:03<00:02, 16.17it/s][A
 58%|█▋ | 58/100 [00:03<00:02, 16.20it/s][A
 60%|█▊ | 60/100 [00:03<00:02, 16.75it/s][A
 62%|█▊ | 62/100 [00:03<00:02, 17.22it/s][A
 64%|█▉ | 64/100 [00:03<00:02, 17.50it/s][A
 66%|█▉ | 66/100 [00:03<00:02, 16.78it/s][A
 68%|██ | 68/100 [00:04<00:01, 17.35it/s][A
 70%|██ | 70/100 [00:04<00:01, 16.79it/s][A
 72%|██▏| 72/100 [00:04<00:01, 17.31it/s][A
 74%|██▏| 74/100 [00:04<00:01, 16.43it/s][A
 77%|██▎| 77/100 [00:04<00:01, 17.05it/s][A
 79%|██▎| 79/100 [00:04<00:01, 17.48it/s][A
 81%|██▍| 81/100 [00:04<00:01, 17.23it/s][A
 84%|██▌| 84/100 [00:04<00:00, 18.43it/s][A
 86%|██▌| 86/100 [00:05<00:00, 17.73it/s][A
 89%|██▋| 89/100 [00:05<00:00, 17.95it/s][A
 91%|██▋| 91/100 [00:05<00:00, 18.29it/s][A
 93%|██▊| 93/100 [00:05<00:00, 17.19it/s][A
 95%|██▊| 95/100 [00:05<00:00, 16.82it/s][A
 97%|██▉| 97/100 [00:05<00:00, 16.89it/s][A
 80%|▊| 800/1000 [13:41<02:28,  1.34it/s]
                                         [A[2026-03-30 14:48:55,637] [INFO] [axolotl.core.trainers.base._save:722] [PID:37135] Saving model checkpoint to /workspace/data/axolotl-outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-800
 80%|▊| 801/1000 [13:44<10:45,  3.25s/it]
 80%|▊| 801/1000 [13:44<10:45,  3.25s/it]
 80%|▊| 802/1000 [13:45<08:15,  2.50s/it]
 80%|▊| 802/1000 [13:45<08:15,  2.50s/it]
 80%|▊| 803/1000 [13:46<06:28,  1.97s/it]
 80%|▊| 803/1000 [13:46<06:28,  1.97s/it]
 80%|▊| 804/1000 [13:46<05:12,  1.59s/it]
 80%|▊| 804/1000 [13:46<05:12,  1.59s/it]