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

fadd720

verified ·

1 Parent(s): ed45871

Training in progress, step 900

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:ad29cff1b863587cbb2ca948354cb20133cf91efb3ab95cc9e09274cb6bcac5b
 size 102264160

 version https://git-lfs.github.com/spec/v1
+oid sha256:92825f995b10c587276dcbb59bd1d6ee8e64825522d2dd1211f3d32eb56271e0
 size 102264160

debug.log CHANGED Viewed

@@ -2114,4 +2114,108 @@ trainable params: 25,559,040 || all params: 2,639,900,928 || trainable%: 0.9682
 85%|▊| 851/1000 [14:30<08:07,  3.27s/it]
 85%|▊| 851/1000 [14:30<08:07,  3.27s/it]
 85%|▊| 852/1000 [14:31<06:12,  2.52s/it]
 85%|▊| 852/1000 [14:31<06:12,  2.52s/it]
 85%|▊| 853/1000 [14:31<04:51,  1.98s/it]
 85%|▊| 853/1000 [14:31<04:51,  1.98s/it]
 85%|▊| 853/1000 [14:31<04:51,  1.98s/it]
 85%|▊| 854/1000 [14:32<03:57,  1.63s/it]
 85%|▊| 854/1000 [14:32<03:57,  1.63s/it]
 86%|▊| 855/1000 [14:33<03:18,  1.37s/it]
 86%|▊| 855/1000 [14:33<03:18,  1.37s/it]
 86%|▊| 856/1000 [14:34<02:52,  1.20s/it]
 86%|▊| 856/1000 [14:34<02:52,  1.20s/it]
 86%|▊| 857/1000 [14:34<02:31,  1.06s/it]
 86%|▊| 857/1000 [14:34<02:31,  1.06s/it]
 86%|▊| 858/1000 [14:35<02:15,  1.05it/s]
 86%|▊| 858/1000 [14:35<02:15,  1.05it/s]
 86%|▊| 859/1000 [14:36<02:07,  1.10it/s]
 86%|▊| 859/1000 [14:36<02:07,  1.10it/s]
 86%|▊| 860/1000 [14:37<02:00,  1.16it/s]
 86%|▊| 860/1000 [14:37<02:00,  1.16it/s]
 86%|▊| 861/1000 [14:37<01:55,  1.21it/s]
 86%|▊| 861/1000 [14:37<01:55,  1.21it/s]
 86%|▊| 862/1000 [14:38<01:50,  1.25it/s]
 86%|▊| 862/1000 [14:38<01:50,  1.25it/s]
 86%|▊| 863/1000 [14:39<01:47,  1.28it/s]
 86%|▊| 863/1000 [14:39<01:47,  1.28it/s]
 86%|▊| 864/1000 [14:40<01:43,  1.31it/s]
 86%|▊| 864/1000 [14:40<01:43,  1.31it/s]
 86%|▊| 865/1000 [14:40<01:42,  1.32it/s]
 86%|▊| 865/1000 [14:40<01:42,  1.32it/s]
 87%|▊| 866/1000 [14:41<01:40,  1.33it/s]
 87%|▊| 866/1000 [14:41<01:40,  1.33it/s]
 87%|▊| 867/1000 [14:42<01:38,  1.35it/s]
 87%|▊| 867/1000 [14:42<01:38,  1.35it/s]
 87%|▊| 868/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 868/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 869/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 869/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 870/1000 [14:44<01:34,  1.37it/s]
 87%|▊| 870/1000 [14:44<01:34,  1.37it/s]
 87%|▊| 871/1000 [14:45<01:36,  1.33it/s]
 87%|▊| 871/1000 [14:45<01:36,  1.33it/s]
 87%|▊| 872/1000 [14:46<01:35,  1.34it/s]
 87%|▊| 872/1000 [14:46<01:35,  1.34it/s]
 87%|▊| 873/1000 [14:46<01:36,  1.32it/s]
 87%|▊| 873/1000 [14:46<01:36,  1.32it/s]
 87%|▊| 874/1000 [14:47<01:36,  1.31it/s]
 87%|▊| 874/1000 [14:47<01:36,  1.31it/s]
 88%|▉| 875/1000 [14:48<01:33,  1.34it/s]
 88%|▉| 875/1000 [14:48<01:33,  1.34it/s]
 88%|▉| 876/1000 [14:49<01:33,  1.32it/s]
 88%|▉| 876/1000 [14:49<01:33,  1.32it/s]
 88%|▉| 877/1000 [14:49<01:34,  1.30it/s]
 88%|▉| 877/1000 [14:49<01:34,  1.30it/s]
 88%|▉| 878/1000 [14:50<01:34,  1.30it/s]
 88%|▉| 878/1000 [14:50<01:34,  1.30it/s]
 88%|▉| 879/1000 [14:51<01:33,  1.30it/s]
 88%|▉| 879/1000 [14:51<01:33,  1.30it/s]
 88%|▉| 880/1000 [14:52<01:33,  1.29it/s]
 88%|▉| 880/1000 [14:52<01:33,  1.29it/s]
 88%|▉| 881/1000 [14:52<01:30,  1.32it/s]
 88%|▉| 881/1000 [14:52<01:30,  1.32it/s]
 88%|▉| 882/1000 [14:53<01:27,  1.35it/s]
 88%|▉| 882/1000 [14:53<01:27,  1.35it/s]
 88%|▉| 883/1000 [14:54<01:25,  1.37it/s]
 88%|▉| 883/1000 [14:54<01:25,  1.37it/s]
 88%|▉| 884/1000 [14:55<01:24,  1.37it/s]
 88%|▉| 884/1000 [14:55<01:24,  1.37it/s]
 88%|▉| 885/1000 [14:55<01:24,  1.36it/s]
 88%|▉| 885/1000 [14:55<01:24,  1.36it/s]
 89%|▉| 886/1000 [14:56<01:24,  1.35it/s]
 89%|▉| 886/1000 [14:56<01:24,  1.35it/s]
 89%|▉| 887/1000 [14:57<01:24,  1.34it/s]
 89%|▉| 887/1000 [14:57<01:24,  1.34it/s]
 89%|▉| 888/1000 [14:58<01:23,  1.34it/s]
 89%|▉| 888/1000 [14:58<01:23,  1.34it/s]
 89%|▉| 889/1000 [14:58<01:22,  1.35it/s]
 89%|▉| 889/1000 [14:58<01:22,  1.35it/s]
 89%|▉| 890/1000 [14:59<01:20,  1.36it/s]
 89%|▉| 890/1000 [14:59<01:20,  1.36it/s]
 89%|▉| 891/1000 [15:00<01:21,  1.33it/s]
 89%|▉| 891/1000 [15:00<01:21,  1.33it/s]
 89%|▉| 892/1000 [15:01<01:20,  1.34it/s]
 89%|▉| 892/1000 [15:01<01:20,  1.34it/s]
 89%|▉| 893/1000 [15:01<01:19,  1.35it/s]
 89%|▉| 893/1000 [15:01<01:19,  1.35it/s]
 89%|▉| 894/1000 [15:02<01:18,  1.36it/s]
 89%|▉| 894/1000 [15:02<01:18,  1.36it/s]
 90%|▉| 895/1000 [15:03<01:19,  1.33it/s]
 90%|▉| 895/1000 [15:03<01:19,  1.33it/s]
 90%|▉| 896/1000 [15:04<01:18,  1.33it/s]
 90%|▉| 896/1000 [15:04<01:18,  1.33it/s]
 90%|▉| 897/1000 [15:04<01:17,  1.33it/s]
 90%|▉| 897/1000 [15:04<01:17,  1.33it/s]
 90%|▉| 898/1000 [15:05<01:17,  1.31it/s]
 90%|▉| 898/1000 [15:05<01:17,  1.31it/s]
 90%|▉| 899/1000 [15:06<01:15,  1.33it/s]
 90%|▉| 899/1000 [15:06<01:15,  1.33it/s]
 90%|▉| 900/1000 [15:07<01:15,  1.33it/s]
 90%|▉| 900/1000 [15:07<01:15,  1.33it/s][2026-03-30 14:50:21,039] [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<00:03, 26.80it/s][A
  6%|▏   | 6/100 [00:00<00:05, 17.42it/s][A
  8%|▎   | 8/100 [00:00<00:05, 17.15it/s][A
 10%|▎  | 10/100 [00:00<00:05, 16.30it/s][A
 12%|▎  | 12/100 [00:00<00:05, 17.18it/s][A
 14%|▍  | 14/100 [00:00<00:05, 17.01it/s][A
 16%|▍  | 16/100 [00:00<00:04, 17.07it/s][A
 18%|▌  | 18/100 [00:01<00:04, 17.24it/s][A
 20%|▌  | 20/100 [00:01<00:04, 17.52it/s][A
 22%|▋  | 22/100 [00:01<00:04, 17.05it/s][A
 24%|▋  | 24/100 [00:01<00:04, 17.67it/s][A
 26%|▊  | 26/100 [00:01<00:04, 17.04it/s][A
 28%|▊  | 28/100 [00:01<00:04, 17.09it/s][A
 30%|▉  | 30/100 [00:01<00:04, 16.70it/s][A
 32%|▉  | 32/100 [00:01<00:04, 16.77it/s][A
 34%|█  | 34/100 [00:01<00:03, 16.88it/s][A
 37%|█  | 37/100 [00:02<00:03, 17.25it/s][A
 39%|█▏ | 39/100 [00:02<00:03, 17.27it/s][A
 41%|█▏ | 41/100 [00:02<00:03, 17.49it/s][A
 44%|█▎ | 44/100 [00:02<00:03, 18.13it/s][A
 46%|█▍ | 46/100 [00:02<00:03, 17.25it/s][A
 48%|█▍ | 48/100 [00:02<00:02, 17.67it/s][A
 50%|█▌ | 50/100 [00:02<00:02, 17.02it/s][A
 52%|█▌ | 52/100 [00:03<00:02, 17.01it/s][A
 54%|█▌ | 54/100 [00:03<00:02, 16.37it/s][A
 56%|█▋ | 56/100 [00:03<00:02, 16.68it/s][A
 58%|█▋ | 58/100 [00:03<00:02, 16.56it/s][A
 60%|█▊ | 60/100 [00:03<00:02, 17.02it/s][A
 62%|█▊ | 62/100 [00:03<00:02, 17.44it/s][A
 64%|█▉ | 64/100 [00:03<00:02, 17.66it/s][A
 66%|█▉ | 66/100 [00:03<00:02, 16.91it/s][A
 68%|██ | 68/100 [00:03<00:01, 17.45it/s][A
 70%|██ | 70/100 [00:04<00:01, 16.84it/s][A
 72%|██▏| 72/100 [00:04<00:01, 17.33it/s][A
 74%|██▏| 74/100 [00:04<00:01, 16.44it/s][A
 77%|██▎| 77/100 [00:04<00:01, 16.46it/s][A
 79%|██▎| 79/100 [00:04<00:01, 17.06it/s][A
 81%|██▍| 81/100 [00:04<00:01, 16.59it/s][A
 84%|██▌| 84/100 [00:04<00:00, 18.12it/s][A
 86%|██▌| 86/100 [00:04<00:00, 17.52it/s][A
 89%|██▋| 89/100 [00:05<00:00, 17.81it/s][A
 91%|██▋| 91/100 [00:05<00:00, 18.20it/s][A
 93%|██▊| 93/100 [00:05<00:00, 17.14it/s][A
 95%|██▊| 95/100 [00:05<00:00, 16.79it/s][A
 97%|██▉| 97/100 [00:05<00:00, 16.87it/s][A
 90%|▉| 900/1000 [15:13<01:15,  1.33it/s]
                                         [A[2026-03-30 14:50:27,075] [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-900
 90%|▉| 901/1000 [15:15<05:14,  3.18s/it]
 90%|▉| 901/1000 [15:15<05:14,  3.18s/it]
 90%|▉| 902/1000 [15:16<04:00,  2.45s/it]
 90%|▉| 902/1000 [15:16<04:00,  2.45s/it]
 90%|▉| 903/1000 [15:17<03:08,  1.94s/it]
 90%|▉| 903/1000 [15:17<03:08,  1.94s/it]
 90%|▉| 904/1000 [15:18<02:31,  1.58s/it]
 90%|▉| 904/1000 [15:18<02:31,  1.58s/it]

 85%|▊| 851/1000 [14:30<08:07,  3.27s/it]
 85%|▊| 851/1000 [14:30<08:07,  3.27s/it]
 85%|▊| 852/1000 [14:31<06:12,  2.52s/it]
 85%|▊| 852/1000 [14:31<06:12,  2.52s/it]
 85%|▊| 853/1000 [14:31<04:51,  1.98s/it]
 85%|▊| 853/1000 [14:31<04:51,  1.98s/it]
 85%|▊| 853/1000 [14:31<04:51,  1.98s/it]
 85%|▊| 854/1000 [14:32<03:57,  1.63s/it]
 85%|▊| 854/1000 [14:32<03:57,  1.63s/it]
 86%|▊| 855/1000 [14:33<03:18,  1.37s/it]
 86%|▊| 855/1000 [14:33<03:18,  1.37s/it]
 86%|▊| 856/1000 [14:34<02:52,  1.20s/it]
 86%|▊| 856/1000 [14:34<02:52,  1.20s/it]
 86%|▊| 857/1000 [14:34<02:31,  1.06s/it]
 86%|▊| 857/1000 [14:34<02:31,  1.06s/it]
 86%|▊| 858/1000 [14:35<02:15,  1.05it/s]
 86%|▊| 858/1000 [14:35<02:15,  1.05it/s]
 86%|▊| 859/1000 [14:36<02:07,  1.10it/s]
 86%|▊| 859/1000 [14:36<02:07,  1.10it/s]
 86%|▊| 860/1000 [14:37<02:00,  1.16it/s]
 86%|▊| 860/1000 [14:37<02:00,  1.16it/s]
 86%|▊| 861/1000 [14:37<01:55,  1.21it/s]
 86%|▊| 861/1000 [14:37<01:55,  1.21it/s]
 86%|▊| 862/1000 [14:38<01:50,  1.25it/s]
 86%|▊| 862/1000 [14:38<01:50,  1.25it/s]
 86%|▊| 863/1000 [14:39<01:47,  1.28it/s]
 86%|▊| 863/1000 [14:39<01:47,  1.28it/s]
 86%|▊| 864/1000 [14:40<01:43,  1.31it/s]
 86%|▊| 864/1000 [14:40<01:43,  1.31it/s]
 86%|▊| 865/1000 [14:40<01:42,  1.32it/s]
 86%|▊| 865/1000 [14:40<01:42,  1.32it/s]
 87%|▊| 866/1000 [14:41<01:40,  1.33it/s]
 87%|▊| 866/1000 [14:41<01:40,  1.33it/s]
 87%|▊| 867/1000 [14:42<01:38,  1.35it/s]
 87%|▊| 867/1000 [14:42<01:38,  1.35it/s]
 87%|▊| 868/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 868/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 869/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 869/1000 [14:43<01:37,  1.35it/s]
 87%|▊| 870/1000 [14:44<01:34,  1.37it/s]
 87%|▊| 870/1000 [14:44<01:34,  1.37it/s]
 87%|▊| 871/1000 [14:45<01:36,  1.33it/s]
 87%|▊| 871/1000 [14:45<01:36,  1.33it/s]
 87%|▊| 872/1000 [14:46<01:35,  1.34it/s]
 87%|▊| 872/1000 [14:46<01:35,  1.34it/s]
 87%|▊| 873/1000 [14:46<01:36,  1.32it/s]
 87%|▊| 873/1000 [14:46<01:36,  1.32it/s]
 87%|▊| 874/1000 [14:47<01:36,  1.31it/s]
 87%|▊| 874/1000 [14:47<01:36,  1.31it/s]
 88%|▉| 875/1000 [14:48<01:33,  1.34it/s]
 88%|▉| 875/1000 [14:48<01:33,  1.34it/s]
 88%|▉| 876/1000 [14:49<01:33,  1.32it/s]
 88%|▉| 876/1000 [14:49<01:33,  1.32it/s]
 88%|▉| 877/1000 [14:49<01:34,  1.30it/s]
 88%|▉| 877/1000 [14:49<01:34,  1.30it/s]
 88%|▉| 878/1000 [14:50<01:34,  1.30it/s]
 88%|▉| 878/1000 [14:50<01:34,  1.30it/s]
 88%|▉| 879/1000 [14:51<01:33,  1.30it/s]
 88%|▉| 879/1000 [14:51<01:33,  1.30it/s]
 88%|▉| 880/1000 [14:52<01:33,  1.29it/s]
 88%|▉| 880/1000 [14:52<01:33,  1.29it/s]
 88%|▉| 881/1000 [14:52<01:30,  1.32it/s]
 88%|▉| 881/1000 [14:52<01:30,  1.32it/s]
 88%|▉| 882/1000 [14:53<01:27,  1.35it/s]
 88%|▉| 882/1000 [14:53<01:27,  1.35it/s]
 88%|▉| 883/1000 [14:54<01:25,  1.37it/s]
 88%|▉| 883/1000 [14:54<01:25,  1.37it/s]
 88%|▉| 884/1000 [14:55<01:24,  1.37it/s]
 88%|▉| 884/1000 [14:55<01:24,  1.37it/s]
 88%|▉| 885/1000 [14:55<01:24,  1.36it/s]
 88%|▉| 885/1000 [14:55<01:24,  1.36it/s]
 89%|▉| 886/1000 [14:56<01:24,  1.35it/s]
 89%|▉| 886/1000 [14:56<01:24,  1.35it/s]
 89%|▉| 887/1000 [14:57<01:24,  1.34it/s]
 89%|▉| 887/1000 [14:57<01:24,  1.34it/s]
 89%|▉| 888/1000 [14:58<01:23,  1.34it/s]
 89%|▉| 888/1000 [14:58<01:23,  1.34it/s]
 89%|▉| 889/1000 [14:58<01:22,  1.35it/s]
 89%|▉| 889/1000 [14:58<01:22,  1.35it/s]
 89%|▉| 890/1000 [14:59<01:20,  1.36it/s]
 89%|▉| 890/1000 [14:59<01:20,  1.36it/s]
 89%|▉| 891/1000 [15:00<01:21,  1.33it/s]
 89%|▉| 891/1000 [15:00<01:21,  1.33it/s]
 89%|▉| 892/1000 [15:01<01:20,  1.34it/s]
 89%|▉| 892/1000 [15:01<01:20,  1.34it/s]
 89%|▉| 893/1000 [15:01<01:19,  1.35it/s]
 89%|▉| 893/1000 [15:01<01:19,  1.35it/s]
 89%|▉| 894/1000 [15:02<01:18,  1.36it/s]
 89%|▉| 894/1000 [15:02<01:18,  1.36it/s]
 90%|▉| 895/1000 [15:03<01:19,  1.33it/s]
 90%|▉| 895/1000 [15:03<01:19,  1.33it/s]
 90%|▉| 896/1000 [15:04<01:18,  1.33it/s]
 90%|▉| 896/1000 [15:04<01:18,  1.33it/s]
 90%|▉| 897/1000 [15:04<01:17,  1.33it/s]
 90%|▉| 897/1000 [15:04<01:17,  1.33it/s]
 90%|▉| 898/1000 [15:05<01:17,  1.31it/s]
 90%|▉| 898/1000 [15:05<01:17,  1.31it/s]
 90%|▉| 899/1000 [15:06<01:15,  1.33it/s]
 90%|▉| 899/1000 [15:06<01:15,  1.33it/s]
 90%|▉| 900/1000 [15:07<01:15,  1.33it/s]
 90%|▉| 900/1000 [15:07<01:15,  1.33it/s][2026-03-30 14:50:21,039] [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<00:03, 26.80it/s][A
  6%|▏   | 6/100 [00:00<00:05, 17.42it/s][A
  8%|▎   | 8/100 [00:00<00:05, 17.15it/s][A
 10%|▎  | 10/100 [00:00<00:05, 16.30it/s][A
 12%|▎  | 12/100 [00:00<00:05, 17.18it/s][A
 14%|▍  | 14/100 [00:00<00:05, 17.01it/s][A
 16%|▍  | 16/100 [00:00<00:04, 17.07it/s][A
 18%|▌  | 18/100 [00:01<00:04, 17.24it/s][A
 20%|▌  | 20/100 [00:01<00:04, 17.52it/s][A
 22%|▋  | 22/100 [00:01<00:04, 17.05it/s][A
 24%|▋  | 24/100 [00:01<00:04, 17.67it/s][A
 26%|▊  | 26/100 [00:01<00:04, 17.04it/s][A
 28%|▊  | 28/100 [00:01<00:04, 17.09it/s][A
 30%|▉  | 30/100 [00:01<00:04, 16.70it/s][A
 32%|▉  | 32/100 [00:01<00:04, 16.77it/s][A
 34%|█  | 34/100 [00:01<00:03, 16.88it/s][A
 37%|█  | 37/100 [00:02<00:03, 17.25it/s][A
 39%|█▏ | 39/100 [00:02<00:03, 17.27it/s][A
 41%|█▏ | 41/100 [00:02<00:03, 17.49it/s][A
 44%|█▎ | 44/100 [00:02<00:03, 18.13it/s][A
 46%|█▍ | 46/100 [00:02<00:03, 17.25it/s][A
 48%|█▍ | 48/100 [00:02<00:02, 17.67it/s][A
 50%|█▌ | 50/100 [00:02<00:02, 17.02it/s][A
 52%|█▌ | 52/100 [00:03<00:02, 17.01it/s][A
 54%|█▌ | 54/100 [00:03<00:02, 16.37it/s][A
 56%|█▋ | 56/100 [00:03<00:02, 16.68it/s][A
 58%|█▋ | 58/100 [00:03<00:02, 16.56it/s][A
 60%|█▊ | 60/100 [00:03<00:02, 17.02it/s][A
 62%|█▊ | 62/100 [00:03<00:02, 17.44it/s][A
 64%|█▉ | 64/100 [00:03<00:02, 17.66it/s][A
 66%|█▉ | 66/100 [00:03<00:02, 16.91it/s][A
 68%|██ | 68/100 [00:03<00:01, 17.45it/s][A
 70%|██ | 70/100 [00:04<00:01, 16.84it/s][A
 72%|██▏| 72/100 [00:04<00:01, 17.33it/s][A
 74%|██▏| 74/100 [00:04<00:01, 16.44it/s][A
 77%|██▎| 77/100 [00:04<00:01, 16.46it/s][A
 79%|██▎| 79/100 [00:04<00:01, 17.06it/s][A
 81%|██▍| 81/100 [00:04<00:01, 16.59it/s][A
 84%|██▌| 84/100 [00:04<00:00, 18.12it/s][A
 86%|██▌| 86/100 [00:04<00:00, 17.52it/s][A
 89%|██▋| 89/100 [00:05<00:00, 17.81it/s][A
 91%|██▋| 91/100 [00:05<00:00, 18.20it/s][A
 93%|██▊| 93/100 [00:05<00:00, 17.14it/s][A
 95%|██▊| 95/100 [00:05<00:00, 16.79it/s][A
 97%|██▉| 97/100 [00:05<00:00, 16.87it/s][A
 90%|▉| 900/1000 [15:13<01:15,  1.33it/s]
                                         [A[2026-03-30 14:50:27,075] [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-900
 90%|▉| 901/1000 [15:15<05:14,  3.18s/it]
 90%|▉| 901/1000 [15:15<05:14,  3.18s/it]
 90%|▉| 902/1000 [15:16<04:00,  2.45s/it]
 90%|▉| 902/1000 [15:16<04:00,  2.45s/it]
 90%|▉| 903/1000 [15:17<03:08,  1.94s/it]
 90%|▉| 903/1000 [15:17<03:08,  1.94s/it]
 90%|▉| 904/1000 [15:18<02:31,  1.58s/it]
 90%|▉| 904/1000 [15:18<02:31,  1.58s/it]