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, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AiAF/rp-2b")
model = AutoModelForMultimodalLM.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

b7c51fa

verified ·

1 Parent(s): 4d9d580

Training in progress, step 700

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
debug.log +104 -1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f324031f7a5f64d996914a53f616440d3542f7bfd1d1bd047c6bf8351b781971
 size 102264160

 version https://git-lfs.github.com/spec/v1
+oid sha256:59badcbc1d668a371853f284e39f9ca33e2fe2af68b773148163044bb0f70bdd
 size 102264160

debug.log CHANGED Viewed

@@ -1702,4 +1702,107 @@ trainable params: 25,559,040 || all params: 2,639,900,928 || trainable%: 0.9682
 65%|▋| 651/1000 [11:27<20:16,  3.49s/it]
 65%|▋| 652/1000 [11:28<15:29,  2.67s/it]
 65%|▋| 652/1000 [11:28<15:29,  2.67s/it]
 65%|▋| 653/1000 [11:29<12:08,  2.10s/it]
 65%|▋| 653/1000 [11:29<12:08,  2.10s/it]
 65%|▋| 654/1000 [11:29<09:50,  1.71s/it]
 65%|▋| 654/1000 [11:29<09:50,  1.71s/it]
 65%|▋| 654/1000 [11:29<09:50,  1.71s/it]
 66%|▋| 655/1000 [11:30<08:09,  1.42s/it]
 66%|▋| 655/1000 [11:30<08:09,  1.42s/it]
 66%|▋| 656/1000 [11:31<06:58,  1.22s/it]
 66%|▋| 656/1000 [11:31<06:58,  1.22s/it]
 66%|▋| 657/1000 [11:32<06:09,  1.08s/it]
 66%|▋| 657/1000 [11:32<06:09,  1.08s/it]
 66%|▋| 658/1000 [11:32<05:34,  1.02it/s]
 66%|▋| 658/1000 [11:32<05:34,  1.02it/s]
 66%|▋| 659/1000 [11:33<05:04,  1.12it/s]
 66%|▋| 659/1000 [11:33<05:04,  1.12it/s]
 66%|▋| 660/1000 [11:34<04:47,  1.18it/s]
 66%|▋| 660/1000 [11:34<04:47,  1.18it/s]
 66%|▋| 661/1000 [11:35<04:32,  1.24it/s]
 66%|▋| 661/1000 [11:35<04:32,  1.24it/s]
 66%|▋| 662/1000 [11:35<04:19,  1.30it/s]
 66%|▋| 662/1000 [11:35<04:19,  1.30it/s]
 66%|▋| 663/1000 [11:36<04:18,  1.30it/s]
 66%|▋| 663/1000 [11:36<04:18,  1.30it/s]
 66%|▋| 664/1000 [11:37<04:19,  1.30it/s]
 66%|▋| 664/1000 [11:37<04:19,  1.30it/s]
 66%|▋| 665/1000 [11:38<04:21,  1.28it/s]
 66%|▋| 665/1000 [11:38<04:21,  1.28it/s]
 67%|▋| 666/1000 [11:38<04:19,  1.29it/s]
 67%|▋| 666/1000 [11:38<04:19,  1.29it/s]
 67%|▋| 667/1000 [11:39<04:14,  1.31it/s]
 67%|▋| 667/1000 [11:39<04:14,  1.31it/s]
 67%|▋| 668/1000 [11:40<04:13,  1.31it/s]
 67%|▋| 668/1000 [11:40<04:13,  1.31it/s]
 67%|▋| 669/1000 [11:41<04:14,  1.30it/s]
 67%|▋| 669/1000 [11:41<04:14,  1.30it/s]
 67%|▋| 670/1000 [11:41<04:12,  1.30it/s]
 67%|▋| 670/1000 [11:41<04:12,  1.30it/s]
 67%|▋| 671/1000 [11:42<04:11,  1.31it/s]
 67%|▋| 671/1000 [11:42<04:11,  1.31it/s]
 67%|▋| 672/1000 [11:43<04:09,  1.31it/s]
 67%|▋| 672/1000 [11:43<04:09,  1.31it/s]
 67%|▋| 673/1000 [11:44<04:07,  1.32it/s]
 67%|▋| 673/1000 [11:44<04:07,  1.32it/s]
 67%|▋| 674/1000 [11:44<04:02,  1.34it/s]
 67%|▋| 674/1000 [11:44<04:02,  1.34it/s]
 68%|▋| 675/1000 [11:45<04:00,  1.35it/s]
 68%|▋| 675/1000 [11:45<04:00,  1.35it/s]
 68%|▋| 676/1000 [11:46<04:03,  1.33it/s]
 68%|▋| 676/1000 [11:46<04:03,  1.33it/s]
 68%|▋| 677/1000 [11:47<04:03,  1.33it/s]
 68%|▋| 677/1000 [11:47<04:03,  1.33it/s]
 68%|▋| 678/1000 [11:47<04:02,  1.33it/s]
 68%|▋| 678/1000 [11:47<04:02,  1.33it/s]
 68%|▋| 679/1000 [11:48<04:02,  1.32it/s]
 68%|▋| 679/1000 [11:48<04:02,  1.32it/s]
 68%|▋| 680/1000 [11:49<04:04,  1.31it/s]
 68%|▋| 680/1000 [11:49<04:04,  1.31it/s]
 68%|▋| 681/1000 [11:50<03:59,  1.33it/s]
 68%|▋| 681/1000 [11:50<03:59,  1.33it/s]
 68%|▋| 682/1000 [11:50<03:56,  1.34it/s]
 68%|▋| 682/1000 [11:50<03:56,  1.34it/s]
 68%|▋| 683/1000 [11:51<03:56,  1.34it/s]
 68%|▋| 683/1000 [11:51<03:56,  1.34it/s]
 68%|▋| 684/1000 [11:52<03:48,  1.38it/s]
 68%|▋| 684/1000 [11:52<03:48,  1.38it/s]
 68%|▋| 685/1000 [11:53<03:49,  1.37it/s]
 68%|▋| 685/1000 [11:53<03:49,  1.37it/s]
 69%|▋| 686/1000 [11:53<03:53,  1.35it/s]
 69%|▋| 686/1000 [11:53<03:53,  1.35it/s]
 69%|▋| 687/1000 [11:54<03:57,  1.32it/s]
 69%|▋| 687/1000 [11:54<03:57,  1.32it/s]
 69%|▋| 688/1000 [11:55<03:48,  1.36it/s]
 69%|▋| 688/1000 [11:55<03:48,  1.36it/s]
 69%|▋| 689/1000 [11:56<03:52,  1.34it/s]
 69%|▋| 689/1000 [11:56<03:52,  1.34it/s]
 69%|▋| 690/1000 [11:56<03:49,  1.35it/s]
 69%|▋| 690/1000 [11:56<03:49,  1.35it/s]
 69%|▋| 691/1000 [11:57<03:46,  1.36it/s]
 69%|▋| 691/1000 [11:57<03:46,  1.36it/s]
 69%|▋| 692/1000 [11:58<03:50,  1.34it/s]
 69%|▋| 692/1000 [11:58<03:50,  1.34it/s]
 69%|▋| 693/1000 [11:59<03:52,  1.32it/s]
 69%|▋| 693/1000 [11:59<03:52,  1.32it/s]
 69%|▋| 694/1000 [11:59<03:45,  1.35it/s]
 69%|▋| 694/1000 [11:59<03:45,  1.35it/s]
 70%|▋| 695/1000 [12:00<03:45,  1.35it/s]
 70%|▋| 695/1000 [12:00<03:45,  1.35it/s]
 70%|▋| 696/1000 [12:01<03:42,  1.36it/s]
 70%|▋| 696/1000 [12:01<03:42,  1.36it/s]
 70%|▋| 697/1000 [12:01<03:39,  1.38it/s]
 70%|▋| 697/1000 [12:01<03:39,  1.38it/s]
 70%|▋| 698/1000 [12:02<03:39,  1.38it/s]
 70%|▋| 698/1000 [12:02<03:39,  1.38it/s]
 70%|▋| 699/1000 [12:03<03:42,  1.35it/s]
 70%|▋| 699/1000 [12:03<03:42,  1.35it/s]
 70%|▋| 700/1000 [12:04<03:40,  1.36it/s]
 70%|▋| 700/1000 [12:04<03:40,  1.36it/s][2026-03-30 14:47:18,171] [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, 29.32it/s][A
  6%|▏   | 6/100 [00:00<00:05, 17.31it/s][A
  8%|▎   | 8/100 [00:00<00:05, 17.08it/s][A
 10%|▎  | 10/100 [00:00<00:05, 16.26it/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, 16.97it/s][A
 18%|▌  | 18/100 [00:01<00:04, 17.16it/s][A
 20%|▌  | 20/100 [00:01<00:04, 17.47it/s][A
 22%|▋  | 22/100 [00:01<00:04, 17.03it/s][A
 24%|▋  | 24/100 [00:01<00:04, 17.66it/s][A
 26%|▊  | 26/100 [00:01<00:04, 17.05it/s][A
 28%|▊  | 28/100 [00:01<00:04, 17.07it/s][A
 30%|▉  | 30/100 [00:01<00:04, 16.62it/s][A
 32%|▉  | 32/100 [00:01<00:04, 16.72it/s][A
 34%|█  | 34/100 [00:01<00:03, 16.86it/s][A
 37%|█  | 37/100 [00:02<00:03, 17.25it/s][A
 39%|█▏ | 39/100 [00:02<00:03, 17.24it/s][A
 41%|█▏ | 41/100 [00:02<00:03, 17.45it/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, 17.00it/s][A
 54%|█▌ | 54/100 [00:03<00:02, 16.32it/s][A
 56%|█▋ | 56/100 [00:03<00:02, 16.62it/s][A
 58%|█▋ | 58/100 [00:03<00:02, 16.50it/s][A
 60%|█▊ | 60/100 [00:03<00:02, 16.98it/s][A
 62%|█▊ | 62/100 [00:03<00:02, 17.41it/s][A
 64%|█▉ | 64/100 [00:03<00:02, 17.57it/s][A
 66%|█▉ | 66/100 [00:03<00:02, 16.85it/s][A
 68%|██ | 68/100 [00:03<00:01, 17.41it/s][A
 70%|██ | 70/100 [00:04<00:01, 16.83it/s][A
 72%|██▏| 72/100 [00:04<00:01, 17.35it/s][A
 74%|██▏| 74/100 [00:04<00:01, 16.46it/s][A
 77%|██▎| 77/100 [00:04<00:01, 17.09it/s][A
 79%|██▎| 79/100 [00:04<00:01, 17.50it/s][A
 81%|██▍| 81/100 [00:04<00:01, 17.24it/s][A
 84%|██▌| 84/100 [00:04<00:00, 18.46it/s][A
 86%|██▌| 86/100 [00:04<00:00, 17.71it/s][A
 89%|██▋| 89/100 [00:05<00:00, 17.91it/s][A
 91%|██▋| 91/100 [00:05<00:00, 18.25it/s][A
 93%|██▊| 93/100 [00:05<00:00, 17.15it/s][A
 95%|██▊| 95/100 [00:05<00:00, 16.80it/s][A
 97%|██▉| 97/100 [00:05<00:00, 16.88it/s][A
 70%|▋| 700/1000 [12:10<03:40,  1.36it/s]
                                         [A[2026-03-30 14:47:24,258] [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-700
 70%|▋| 701/1000 [12:13<16:05,  3.23s/it]
 70%|▋| 701/1000 [12:13<16:05,  3.23s/it]
 70%|▋| 702/1000 [12:13<12:18,  2.48s/it]
 70%|▋| 702/1000 [12:13<12:18,  2.48s/it]
 70%|▋| 703/1000 [12:14<09:46,  1.97s/it]
 70%|▋| 703/1000 [12:14<09:46,  1.97s/it]
 70%|▋| 704/1000 [12:15<07:54,  1.60s/it]
 70%|▋| 704/1000 [12:15<07:54,  1.60s/it]

 65%|▋| 651/1000 [11:27<20:16,  3.49s/it]
 65%|▋| 652/1000 [11:28<15:29,  2.67s/it]
 65%|▋| 652/1000 [11:28<15:29,  2.67s/it]
 65%|▋| 653/1000 [11:29<12:08,  2.10s/it]
 65%|▋| 653/1000 [11:29<12:08,  2.10s/it]
 65%|▋| 654/1000 [11:29<09:50,  1.71s/it]
 65%|▋| 654/1000 [11:29<09:50,  1.71s/it]
 65%|▋| 654/1000 [11:29<09:50,  1.71s/it]
 66%|▋| 655/1000 [11:30<08:09,  1.42s/it]
 66%|▋| 655/1000 [11:30<08:09,  1.42s/it]
 66%|▋| 656/1000 [11:31<06:58,  1.22s/it]
 66%|▋| 656/1000 [11:31<06:58,  1.22s/it]
 66%|▋| 657/1000 [11:32<06:09,  1.08s/it]
 66%|▋| 657/1000 [11:32<06:09,  1.08s/it]
 66%|▋| 658/1000 [11:32<05:34,  1.02it/s]
 66%|▋| 658/1000 [11:32<05:34,  1.02it/s]
 66%|▋| 659/1000 [11:33<05:04,  1.12it/s]
 66%|▋| 659/1000 [11:33<05:04,  1.12it/s]
 66%|▋| 660/1000 [11:34<04:47,  1.18it/s]
 66%|▋| 660/1000 [11:34<04:47,  1.18it/s]
 66%|▋| 661/1000 [11:35<04:32,  1.24it/s]
 66%|▋| 661/1000 [11:35<04:32,  1.24it/s]
 66%|▋| 662/1000 [11:35<04:19,  1.30it/s]
 66%|▋| 662/1000 [11:35<04:19,  1.30it/s]
 66%|▋| 663/1000 [11:36<04:18,  1.30it/s]
 66%|▋| 663/1000 [11:36<04:18,  1.30it/s]
 66%|▋| 664/1000 [11:37<04:19,  1.30it/s]
 66%|▋| 664/1000 [11:37<04:19,  1.30it/s]
 66%|▋| 665/1000 [11:38<04:21,  1.28it/s]
 66%|▋| 665/1000 [11:38<04:21,  1.28it/s]
 67%|▋| 666/1000 [11:38<04:19,  1.29it/s]
 67%|▋| 666/1000 [11:38<04:19,  1.29it/s]
 67%|▋| 667/1000 [11:39<04:14,  1.31it/s]
 67%|▋| 667/1000 [11:39<04:14,  1.31it/s]
 67%|▋| 668/1000 [11:40<04:13,  1.31it/s]
 67%|▋| 668/1000 [11:40<04:13,  1.31it/s]
 67%|▋| 669/1000 [11:41<04:14,  1.30it/s]
 67%|▋| 669/1000 [11:41<04:14,  1.30it/s]
 67%|▋| 670/1000 [11:41<04:12,  1.30it/s]
 67%|▋| 670/1000 [11:41<04:12,  1.30it/s]
 67%|▋| 671/1000 [11:42<04:11,  1.31it/s]
 67%|▋| 671/1000 [11:42<04:11,  1.31it/s]
 67%|▋| 672/1000 [11:43<04:09,  1.31it/s]
 67%|▋| 672/1000 [11:43<04:09,  1.31it/s]
 67%|▋| 673/1000 [11:44<04:07,  1.32it/s]
 67%|▋| 673/1000 [11:44<04:07,  1.32it/s]
 67%|▋| 674/1000 [11:44<04:02,  1.34it/s]
 67%|▋| 674/1000 [11:44<04:02,  1.34it/s]
 68%|▋| 675/1000 [11:45<04:00,  1.35it/s]
 68%|▋| 675/1000 [11:45<04:00,  1.35it/s]
 68%|▋| 676/1000 [11:46<04:03,  1.33it/s]
 68%|▋| 676/1000 [11:46<04:03,  1.33it/s]
 68%|▋| 677/1000 [11:47<04:03,  1.33it/s]
 68%|▋| 677/1000 [11:47<04:03,  1.33it/s]
 68%|▋| 678/1000 [11:47<04:02,  1.33it/s]
 68%|▋| 678/1000 [11:47<04:02,  1.33it/s]
 68%|▋| 679/1000 [11:48<04:02,  1.32it/s]
 68%|▋| 679/1000 [11:48<04:02,  1.32it/s]
 68%|▋| 680/1000 [11:49<04:04,  1.31it/s]
 68%|▋| 680/1000 [11:49<04:04,  1.31it/s]
 68%|▋| 681/1000 [11:50<03:59,  1.33it/s]
 68%|▋| 681/1000 [11:50<03:59,  1.33it/s]
 68%|▋| 682/1000 [11:50<03:56,  1.34it/s]
 68%|▋| 682/1000 [11:50<03:56,  1.34it/s]
 68%|▋| 683/1000 [11:51<03:56,  1.34it/s]
 68%|▋| 683/1000 [11:51<03:56,  1.34it/s]
 68%|▋| 684/1000 [11:52<03:48,  1.38it/s]
 68%|▋| 684/1000 [11:52<03:48,  1.38it/s]
 68%|▋| 685/1000 [11:53<03:49,  1.37it/s]
 68%|▋| 685/1000 [11:53<03:49,  1.37it/s]
 69%|▋| 686/1000 [11:53<03:53,  1.35it/s]
 69%|▋| 686/1000 [11:53<03:53,  1.35it/s]
 69%|▋| 687/1000 [11:54<03:57,  1.32it/s]
 69%|▋| 687/1000 [11:54<03:57,  1.32it/s]
 69%|▋| 688/1000 [11:55<03:48,  1.36it/s]
 69%|▋| 688/1000 [11:55<03:48,  1.36it/s]
 69%|▋| 689/1000 [11:56<03:52,  1.34it/s]
 69%|▋| 689/1000 [11:56<03:52,  1.34it/s]
 69%|▋| 690/1000 [11:56<03:49,  1.35it/s]
 69%|▋| 690/1000 [11:56<03:49,  1.35it/s]
 69%|▋| 691/1000 [11:57<03:46,  1.36it/s]
 69%|▋| 691/1000 [11:57<03:46,  1.36it/s]
 69%|▋| 692/1000 [11:58<03:50,  1.34it/s]
 69%|▋| 692/1000 [11:58<03:50,  1.34it/s]
 69%|▋| 693/1000 [11:59<03:52,  1.32it/s]
 69%|▋| 693/1000 [11:59<03:52,  1.32it/s]
 69%|▋| 694/1000 [11:59<03:45,  1.35it/s]
 69%|▋| 694/1000 [11:59<03:45,  1.35it/s]
 70%|▋| 695/1000 [12:00<03:45,  1.35it/s]
 70%|▋| 695/1000 [12:00<03:45,  1.35it/s]
 70%|▋| 696/1000 [12:01<03:42,  1.36it/s]
 70%|▋| 696/1000 [12:01<03:42,  1.36it/s]
 70%|▋| 697/1000 [12:01<03:39,  1.38it/s]
 70%|▋| 697/1000 [12:01<03:39,  1.38it/s]
 70%|▋| 698/1000 [12:02<03:39,  1.38it/s]
 70%|▋| 698/1000 [12:02<03:39,  1.38it/s]
 70%|▋| 699/1000 [12:03<03:42,  1.35it/s]
 70%|▋| 699/1000 [12:03<03:42,  1.35it/s]
 70%|▋| 700/1000 [12:04<03:40,  1.36it/s]
 70%|▋| 700/1000 [12:04<03:40,  1.36it/s][2026-03-30 14:47:18,171] [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, 29.32it/s][A
  6%|▏   | 6/100 [00:00<00:05, 17.31it/s][A
  8%|▎   | 8/100 [00:00<00:05, 17.08it/s][A
 10%|▎  | 10/100 [00:00<00:05, 16.26it/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, 16.97it/s][A
 18%|▌  | 18/100 [00:01<00:04, 17.16it/s][A
 20%|▌  | 20/100 [00:01<00:04, 17.47it/s][A
 22%|▋  | 22/100 [00:01<00:04, 17.03it/s][A
 24%|▋  | 24/100 [00:01<00:04, 17.66it/s][A
 26%|▊  | 26/100 [00:01<00:04, 17.05it/s][A
 28%|▊  | 28/100 [00:01<00:04, 17.07it/s][A
 30%|▉  | 30/100 [00:01<00:04, 16.62it/s][A
 32%|▉  | 32/100 [00:01<00:04, 16.72it/s][A
 34%|█  | 34/100 [00:01<00:03, 16.86it/s][A
 37%|█  | 37/100 [00:02<00:03, 17.25it/s][A
 39%|█▏ | 39/100 [00:02<00:03, 17.24it/s][A
 41%|█▏ | 41/100 [00:02<00:03, 17.45it/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, 17.00it/s][A
 54%|█▌ | 54/100 [00:03<00:02, 16.32it/s][A
 56%|█▋ | 56/100 [00:03<00:02, 16.62it/s][A
 58%|█▋ | 58/100 [00:03<00:02, 16.50it/s][A
 60%|█▊ | 60/100 [00:03<00:02, 16.98it/s][A
 62%|█▊ | 62/100 [00:03<00:02, 17.41it/s][A
 64%|█▉ | 64/100 [00:03<00:02, 17.57it/s][A
 66%|█▉ | 66/100 [00:03<00:02, 16.85it/s][A
 68%|██ | 68/100 [00:03<00:01, 17.41it/s][A
 70%|██ | 70/100 [00:04<00:01, 16.83it/s][A
 72%|██▏| 72/100 [00:04<00:01, 17.35it/s][A
 74%|██▏| 74/100 [00:04<00:01, 16.46it/s][A
 77%|██▎| 77/100 [00:04<00:01, 17.09it/s][A
 79%|██▎| 79/100 [00:04<00:01, 17.50it/s][A
 81%|██▍| 81/100 [00:04<00:01, 17.24it/s][A
 84%|██▌| 84/100 [00:04<00:00, 18.46it/s][A
 86%|██▌| 86/100 [00:04<00:00, 17.71it/s][A
 89%|██▋| 89/100 [00:05<00:00, 17.91it/s][A
 91%|██▋| 91/100 [00:05<00:00, 18.25it/s][A
 93%|██▊| 93/100 [00:05<00:00, 17.15it/s][A
 95%|██▊| 95/100 [00:05<00:00, 16.80it/s][A
 97%|██▉| 97/100 [00:05<00:00, 16.88it/s][A
 70%|▋| 700/1000 [12:10<03:40,  1.36it/s]
                                         [A[2026-03-30 14:47:24,258] [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-700
 70%|▋| 701/1000 [12:13<16:05,  3.23s/it]
 70%|▋| 701/1000 [12:13<16:05,  3.23s/it]
 70%|▋| 702/1000 [12:13<12:18,  2.48s/it]
 70%|▋| 702/1000 [12:13<12:18,  2.48s/it]
 70%|▋| 703/1000 [12:14<09:46,  1.97s/it]
 70%|▋| 703/1000 [12:14<09:46,  1.97s/it]
 70%|▋| 704/1000 [12:15<07:54,  1.60s/it]
 70%|▋| 704/1000 [12:15<07:54,  1.60s/it]