Instructions to use iamjayeshc/ArgParser-v1-Qwen0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamjayeshc/ArgParser-v1-Qwen0.5B with Transformers:

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

pipe = pipeline("text-generation", model="iamjayeshc/ArgParser-v1-Qwen0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamjayeshc/ArgParser-v1-Qwen0.5B")
model = AutoModelForCausalLM.from_pretrained("iamjayeshc/ArgParser-v1-Qwen0.5B", device_map="auto")
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]:]))

PEFT
How to use iamjayeshc/ArgParser-v1-Qwen0.5B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iamjayeshc/ArgParser-v1-Qwen0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamjayeshc/ArgParser-v1-Qwen0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamjayeshc/ArgParser-v1-Qwen0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/iamjayeshc/ArgParser-v1-Qwen0.5B

SGLang

How to use iamjayeshc/ArgParser-v1-Qwen0.5B 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 "iamjayeshc/ArgParser-v1-Qwen0.5B" \
    --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": "iamjayeshc/ArgParser-v1-Qwen0.5B",
		"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 "iamjayeshc/ArgParser-v1-Qwen0.5B" \
        --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": "iamjayeshc/ArgParser-v1-Qwen0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use iamjayeshc/ArgParser-v1-Qwen0.5B with Docker Model Runner:
```
docker model run hf.co/iamjayeshc/ArgParser-v1-Qwen0.5B
```

ArgParser-v1-Qwen0.5B

File size: 39,589 Bytes

c706dc3

Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
[train-β] config: configs/phase2_beta_qwen1.5b.yaml
[train-β] unified dir: phase2_data/unified
[train-β] excluding sources: ('liararg',)
[unified] loaded 2450 records across 4 source(s):
  abstrct: 700
  cdcp: 731
  microtext: 112
  perspectrum: 907
[train-β] split distribution: {'test': 688, 'train': 1494, 'val': 268}
[train-β] building student: hf (Qwen/Qwen2.5-0.5B-Instruct)
[student:hf] base_model=Qwen/Qwen2.5-0.5B-Instruct (seq2seq=False)

Loading weights:   0%|          | 0/290 [00:00<?, ?it/s]
Loading weights:   0%|          | 1/290 [00:01<05:06,  1.06s/it]
Loading weights:  84%|████████▍ | 243/290 [00:01<00:00, 288.20it/s]
Loading weights: 100%|██████████| 290/290 [00:01<00:00, 227.75it/s]
[transformers] warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
[student:hf] encoding 1494 train + 268 val records (causal format)

  0%|          | 0/141 [00:00<?, ?it/s]/home/users/jchoudhari/argument-aware-rag/.venv/lib/python3.10/site-packages/torch/utils/checkpoint.py:1399: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
  with device_autocast_ctx, torch.cpu.amp.autocast(**cpu_autocast_kwargs), recompute_context:  # type: ignore[attr-defined]

  1%|          | 1/141 [00:48<1:53:06, 48.47s/it]
  1%|▏         | 2/141 [01:26<1:37:35, 42.13s/it]
  2%|▏         | 3/141 [02:04<1:33:18, 40.57s/it]
  3%|▎         | 4/141 [02:44<1:31:57, 40.27s/it]
  4%|▎         | 5/141 [03:22<1:29:00, 39.27s/it]
  4%|▍         | 6/141 [03:59<1:26:30, 38.45s/it]
  5%|▍         | 7/141 [04:36<1:25:03, 38.08s/it]
  6%|▌         | 8/141 [05:15<1:25:18, 38.48s/it]
  6%|▋         | 9/141 [05:53<1:24:15, 38.30s/it]
  7%|▋         | 10/141 [06:28<1:21:36, 37.38s/it]
  8%|▊         | 11/141 [07:01<1:18:03, 36.02s/it]
  9%|▊         | 12/141 [07:35<1:16:10, 35.43s/it]
  9%|▉         | 13/141 [08:11<1:15:55, 35.59s/it]
 10%|▉         | 14/141 [08:47<1:15:19, 35.58s/it]
 11%|█         | 15/141 [09:25<1:15:57, 36.17s/it]
 11%|█▏        | 16/141 [10:02<1:16:08, 36.55s/it]
 12%|█▏        | 17/141 [10:42<1:17:38, 37.57s/it]
 13%|█▎        | 18/141 [11:21<1:17:55, 38.01s/it]
 13%|█▎        | 19/141 [12:00<1:18:15, 38.48s/it]
 14%|█▍        | 20/141 [12:37<1:16:11, 37.78s/it]
 15%|█▍        | 21/141 [13:14<1:15:30, 37.75s/it]
 16%|█▌        | 22/141 [13:49<1:13:07, 36.87s/it]
 16%|█▋        | 23/141 [14:28<1:13:47, 37.53s/it]
 17%|█▋        | 24/141 [15:05<1:13:00, 37.44s/it]
 18%|█▊        | 25/141 [15:41<1:11:04, 36.77s/it]
 18%|█▊        | 26/141 [16:15<1:09:08, 36.08s/it]
 19%|█▉        | 27/141 [16:54<1:10:15, 36.98s/it]
 20%|█▉        | 28/141 [17:31<1:09:31, 36.92s/it]
 21%|██        | 29/141 [18:11<1:10:31, 37.79s/it]
 21%|██▏       | 30/141 [18:48<1:09:31, 37.58s/it]
 22%|██▏       | 31/141 [19:27<1:09:42, 38.02s/it]
 23%|██▎       | 32/141 [20:05<1:09:13, 38.10s/it]
 23%|██▎       | 33/141 [20:43<1:08:15, 37.93s/it]
 24%|██▍       | 34/141 [21:19<1:06:31, 37.30s/it]
 25%|██▍       | 35/141 [21:54<1:05:05, 36.85s/it]
 26%|██▌       | 36/141 [22:29<1:03:16, 36.16s/it]
 26%|██▌       | 37/141 [23:05<1:02:35, 36.11s/it]
 27%|██▋       | 38/141 [23:43<1:02:50, 36.61s/it]
 28%|██▊       | 39/141 [24:19<1:01:53, 36.41s/it]
 28%|██▊       | 40/141 [24:58<1:02:49, 37.33s/it]
 29%|██▉       | 41/141 [25:36<1:02:41, 37.62s/it]
 30%|██▉       | 42/141 [26:14<1:02:00, 37.58s/it]
 30%|███       | 43/141 [26:52<1:01:46, 37.82s/it]
 31%|███       | 44/141 [27:31<1:01:21, 37.95s/it]
 32%|███▏      | 45/141 [28:07<1:00:12, 37.63s/it]
 33%|███▎      | 46/141 [28:46<1:00:04, 37.94s/it]
 33%|███▎      | 47/141 [29:11<53:16, 34.01s/it]  

  0%|          | 0/134 [00:00<?, ?it/s][A

  1%|▏         | 2/134 [00:00<00:30,  4.31it/s][A

  2%|▏         | 3/134 [00:00<00:43,  3.03it/s][A

  3%|▎         | 4/134 [00:01<00:50,  2.56it/s][A

  4%|▎         | 5/134 [00:01<00:57,  2.26it/s][A

  4%|▍         | 6/134 [00:02<01:00,  2.13it/s][A

  5%|▌         | 7/134 [00:02<01:01,  2.08it/s][A

  6%|▌         | 8/134 [00:03<01:00,  2.07it/s][A

  7%|▋         | 9/134 [00:04<01:04,  1.94it/s][A

  7%|▋         | 10/134 [00:04<01:07,  1.85it/s][A

  8%|▊         | 11/134 [00:05<01:07,  1.81it/s][A

  9%|▉         | 12/134 [00:05<01:08,  1.78it/s][A

 10%|▉         | 13/134 [00:06<01:05,  1.86it/s][A

 10%|█         | 14/134 [00:06<01:05,  1.84it/s][A

 11%|█         | 15/134 [00:07<01:06,  1.78it/s][A

 12%|█▏        | 16/134 [00:07<01:04,  1.83it/s][A

 13%|█▎        | 17/134 [00:08<01:02,  1.87it/s][A

 13%|█▎        | 18/134 [00:08<01:00,  1.91it/s][A

 14%|█▍        | 19/134 [00:09<00:59,  1.93it/s][A

 15%|█▍        | 20/134 [00:10<01:00,  1.89it/s][A

 16%|█▌        | 21/134 [00:10<01:03,  1.77it/s][A

 16%|█▋        | 22/134 [00:11<01:03,  1.75it/s][A

 17%|█▋        | 23/134 [00:11<01:02,  1.77it/s][A

 18%|█▊        | 24/134 [00:12<01:03,  1.74it/s][A

 19%|█▊        | 25/134 [00:12<01:00,  1.79it/s][A

 19%|█▉        | 26/134 [00:13<01:00,  1.77it/s][A

 20%|██        | 27/134 [00:14<01:03,  1.68it/s][A

 21%|██        | 28/134 [00:14<01:05,  1.62it/s][A

 22%|██▏       | 29/134 [00:15<01:05,  1.60it/s][A

 22%|██▏       | 30/134 [00:16<01:06,  1.57it/s][A

 23%|██▎       | 31/134 [00:16<01:06,  1.55it/s][A

 24%|██▍       | 32/134 [00:17<01:06,  1.54it/s][A

 25%|██▍       | 33/134 [00:18<01:06,  1.51it/s][A

 25%|██▌       | 34/134 [00:18<01:06,  1.51it/s][A

 26%|██▌       | 35/134 [00:19<01:05,  1.52it/s][A

 27%|██▋       | 36/134 [00:20<01:03,  1.54it/s][A

 28%|██▊       | 37/134 [00:20<01:03,  1.54it/s][A

 28%|██▊       | 38/134 [00:21<01:02,  1.52it/s][A

 29%|██▉       | 39/134 [00:22<01:02,  1.53it/s][A

 30%|██▉       | 40/134 [00:22<01:01,  1.53it/s][A

 31%|███       | 41/134 [00:23<01:01,  1.52it/s][A

 31%|███▏      | 42/134 [00:24<01:00,  1.51it/s][A

 32%|███▏      | 43/134 [00:24<01:00,  1.51it/s][A

 33%|███▎      | 44/134 [00:25<00:59,  1.52it/s][A

 34%|███▎      | 45/134 [00:26<00:58,  1.53it/s][A

 34%|███▍      | 46/134 [00:26<00:57,  1.53it/s][A

 35%|███▌      | 47/134 [00:27<00:56,  1.53it/s][A

 36%|███▌      | 48/134 [00:28<00:56,  1.53it/s][A

 37%|███▋      | 49/134 [00:28<00:54,  1.57it/s][A

 37%|███▋      | 50/134 [00:29<00:51,  1.62it/s][A

 38%|███▊      | 51/134 [00:29<00:51,  1.60it/s][A

 39%|███▉      | 52/134 [00:30<00:52,  1.57it/s][A

 40%|███▉      | 53/134 [00:31<00:51,  1.56it/s][A

 40%|████      | 54/134 [00:31<00:50,  1.57it/s][A

 41%|████      | 55/134 [00:32<00:50,  1.57it/s][A

 42%|████▏     | 56/134 [00:33<00:50,  1.55it/s][A

 43%|████▎     | 57/134 [00:33<00:49,  1.54it/s][A

 43%|████▎     | 58/134 [00:34<00:49,  1.54it/s][A

 44%|████▍     | 59/134 [00:35<00:48,  1.55it/s][A

 45%|████▍     | 60/134 [00:35<00:47,  1.55it/s][A

 46%|████▌     | 61/134 [00:36<00:47,  1.54it/s][A

 46%|████▋     | 62/134 [00:36<00:46,  1.54it/s][A

 47%|████▋     | 63/134 [00:37<00:46,  1.53it/s][A

 48%|████▊     | 64/134 [00:38<00:45,  1.52it/s][A

 49%|████▊     | 65/134 [00:38<00:45,  1.52it/s][A

 49%|████▉     | 66/134 [00:39<00:43,  1.57it/s][A

 50%|█████     | 67/134 [00:40<00:40,  1.67it/s][A

 51%|█████     | 68/134 [00:40<00:37,  1.76it/s][A

 51%|█████▏    | 69/134 [00:41<00:37,  1.75it/s][A

 52%|█████▏    | 70/134 [00:41<00:36,  1.74it/s][A

 53%|█████▎    | 71/134 [00:42<00:35,  1.80it/s][A

 54%|█████▎    | 72/134 [00:42<00:33,  1.85it/s][A

 54%|█████▍    | 73/134 [00:43<00:33,  1.81it/s][A

 55%|█████▌    | 74/134 [00:43<00:33,  1.77it/s][A

 56%|█████▌    | 75/134 [00:44<00:32,  1.81it/s][A

 57%|█████▋    | 76/134 [00:44<00:31,  1.86it/s][A

 57%|█████▋    | 77/134 [00:45<00:29,  1.91it/s][A

 58%|█████▊    | 78/134 [00:45<00:29,  1.89it/s][A

 59%|█████▉    | 79/134 [00:46<00:29,  1.84it/s][A

 60%|█████▉    | 80/134 [00:47<00:28,  1.91it/s][A

 60%|██████    | 81/134 [00:47<00:27,  1.95it/s][A

 61%|██████    | 82/134 [00:47<00:26,  1.98it/s][A

 62%|██████▏   | 83/134 [00:48<00:25,  1.99it/s][A

 63%|██████▎   | 84/134 [00:48<00:24,  2.01it/s][A

 63%|██████▎   | 85/134 [00:49<00:25,  1.93it/s][A

 64%|██████▍   | 86/134 [00:50<00:25,  1.85it/s][A

 65%|██████▍   | 87/134 [00:50<00:25,  1.83it/s][A

 66%|██████▌   | 88/134 [00:51<00:25,  1.78it/s][A

 66%|██████▋   | 89/134 [00:51<00:24,  1.83it/s][A

 67%|██████▋   | 90/134 [00:52<00:23,  1.85it/s][A

 68%|██████▊   | 91/134 [00:52<00:22,  1.88it/s][A

 69%|██████▊   | 92/134 [00:53<00:22,  1.91it/s][A

 69%|██████▉   | 93/134 [00:53<00:21,  1.92it/s][A

 70%|███████   | 94/134 [00:54<00:20,  1.94it/s][A

 71%|███████   | 95/134 [00:54<00:19,  1.98it/s][A

 72%|███████▏  | 96/134 [00:55<00:19,  2.00it/s][A

 72%|███████▏  | 97/134 [00:55<00:18,  1.99it/s][A

 73%|███████▎  | 98/134 [00:56<00:19,  1.89it/s][A

 74%|███████▍  | 99/134 [00:57<00:19,  1.83it/s][A

 75%|███████▍  | 100/134 [00:57<00:18,  1.88it/s][A

 75%|███████▌  | 101/134 [00:58<00:17,  1.91it/s][A

 76%|███████▌  | 102/134 [00:58<00:16,  1.97it/s][A

 77%|███████▋  | 103/134 [00:58<00:15,  1.98it/s][A

 78%|███████▊  | 104/134 [00:59<00:15,  1.96it/s][A

 78%|███████▊  | 105/134 [01:00<00:14,  1.96it/s][A

 79%|███████▉  | 106/134 [01:00<00:14,  1.91it/s][A

 80%|███████▉  | 107/134 [01:01<00:14,  1.86it/s][A

 81%|████████  | 108/134 [01:01<00:13,  1.91it/s][A

 81%|████████▏ | 109/134 [01:02<00:12,  1.93it/s][A

 82%|████████▏ | 110/134 [01:02<00:12,  1.96it/s][A

 83%|████████▎ | 111/134 [01:03<00:11,  1.97it/s][A

 84%|████████▎ | 112/134 [01:03<00:11,  1.97it/s][A

 84%|████████▍ | 113/134 [01:04<00:10,  1.98it/s][A

 85%|████████▌ | 114/134 [01:04<00:09,  2.02it/s][A

 86%|████████▌ | 115/134 [01:05<00:09,  2.05it/s][A

 87%|████████▋ | 116/134 [01:05<00:09,  1.99it/s][A

 87%|████████▋ | 117/134 [01:06<00:08,  1.90it/s][A

 88%|████████▊ | 118/134 [01:06<00:08,  1.93it/s][A

 89%|████████▉ | 119/134 [01:07<00:07,  1.89it/s][A

 90%|████████▉ | 120/134 [01:07<00:07,  1.82it/s][A

 90%|█████████ | 121/134 [01:08<00:06,  1.88it/s][A

 91%|█████████ | 122/134 [01:08<00:06,  1.90it/s][A

 92%|█████████▏| 123/134 [01:09<00:05,  1.92it/s][A

 93%|█████████▎| 124/134 [01:09<00:05,  1.93it/s][A

 93%|█████████▎| 125/134 [01:10<00:04,  1.93it/s][A

 94%|█████████▍| 126/134 [01:10<00:04,  1.94it/s][A

 95%|█████████▍| 127/134 [01:11<00:03,  1.89it/s][A

 96%|█████████▌| 128/134 [01:12<00:03,  1.83it/s][A

 96%|█████████▋| 129/134 [01:12<00:02,  1.81it/s][A

 97%|█████████▋| 130/134 [01:13<00:02,  1.77it/s][A

 98%|█████████▊| 131/134 [01:13<00:01,  1.77it/s][A

 99%|█████████▊| 132/134 [01:14<00:01,  1.72it/s][A

 99%|█████████▉| 133/134 [01:14<00:00,  1.73it/s][A

100%|██████████| 134/134 [01:15<00:00,  1.70it/s][A
                                                


                                                 
[A
 33%|███▎      | 47/141 [30:27<53:16, 34.01s/it]

100%|██████████| 134/134 [01:15<00:00,  1.70it/s][A

                                                 [A{'eval_loss': 'nan', 'eval_runtime': '76.08', 'eval_samples_per_second': '3.522', 'eval_steps_per_second': '1.761', 'epoch': '1'}


Writing model shards:   0%|          | 0/1 [00:00<?, ?it/s][A

Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.58s/it][A
Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.58s/it]
/home/users/jchoudhari/argument-aware-rag/.venv/lib/python3.10/site-packages/torch/utils/checkpoint.py:1399: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
  with device_autocast_ctx, torch.cpu.amp.autocast(**cpu_autocast_kwargs), recompute_context:  # type: ignore[attr-defined]

 34%|███▍      | 48/141 [31:11<1:32:51, 59.90s/it]
 35%|███▍      | 49/141 [31:49<1:21:34, 53.20s/it]
 35%|███▌      | 50/141 [32:25<1:13:07, 48.22s/it]
                                                  

 35%|███▌      | 50/141 [32:25<1:13:07, 48.22s/it]
 36%|███▌      | 51/141 [33:01<1:06:52, 44.58s/it]
 37%|███▋      | 52/141 [33:39<1:02:57, 42.45s/it]
 38%|███▊      | 53/141 [34:14<59:05, 40.29s/it]  
 38%|███▊      | 54/141 [34:55<58:43, 40.49s/it]
 39%|███▉      | 55/141 [35:31<56:07, 39.15s/it]
 40%|███▉      | 56/141 [36:08<54:29, 38.47s/it]
 40%|████      | 57/141 [36:47<54:09, 38.69s/it]
 41%|████      | 58/141 [37:25<53:02, 38.35s/it]
 42%|████▏     | 59/141 [38:02<52:06, 38.12s/it]
 43%|████▎     | 60/141 [38:39<50:53, 37.69s/it]
 43%|████▎     | 61/141 [39:16<49:55, 37.45s/it]
 44%|████▍     | 62/141 [39:55<49:47, 37.82s/it]
 45%|████▍     | 63/141 [40:31<48:46, 37.52s/it]
 45%|████▌     | 64/141 [41:08<47:54, 37.34s/it]
 46%|████▌     | 65/141 [41:47<47:52, 37.80s/it]
 47%|████▋     | 66/141 [42:24<46:55, 37.54s/it]
 48%|████▊     | 67/141 [43:03<46:43, 37.88s/it]
 48%|████▊     | 68/141 [43:38<44:56, 36.94s/it]
 49%|████▉     | 69/141 [44:15<44:36, 37.18s/it]
 50%|████▉     | 70/141 [44:52<43:45, 36.98s/it]
 50%|█████     | 71/141 [45:29<43:08, 36.98s/it]
 51%|█████     | 72/141 [46:05<42:14, 36.73s/it]
 52%|█████▏    | 73/141 [46:44<42:29, 37.50s/it]
 52%|█████▏    | 74/141 [47:23<42:14, 37.83s/it]
 53%|█████▎    | 75/141 [47:59<40:56, 37.21s/it]
 54%|█████▍    | 76/141 [48:36<40:27, 37.35s/it]
 55%|█████▍    | 77/141 [49:14<39:59, 37.49s/it]
 55%|█████▌    | 78/141 [49:51<39:16, 37.40s/it]
 56%|█████▌    | 79/141 [50:28<38:32, 37.29s/it]
 57%|█████▋    | 80/141 [51:05<37:48, 37.19s/it]
 57%|█████▋    | 81/141 [51:44<37:42, 37.70s/it]
 58%|█████▊    | 82/141 [52:22<37:03, 37.68s/it]
 59%|█████▉    | 83/141 [53:01<36:41, 37.96s/it]
 60%|█████▉    | 84/141 [53:38<35:47, 37.68s/it]
 60%|██████    | 85/141 [54:14<34:57, 37.46s/it]
 61%|██████    | 86/141 [54:51<34:04, 37.17s/it]
 62%|██████▏   | 87/141 [55:28<33:21, 37.06s/it]
 62%|██████▏   | 88/141 [56:07<33:14, 37.62s/it]
 63%|██████▎   | 89/141 [56:45<32:47, 37.84s/it]
 64%|██████▍   | 90/141 [57:23<32:15, 37.95s/it]
 65%|██████▍   | 91/141 [58:02<31:46, 38.13s/it]
 65%|██████▌   | 92/141 [58:39<30:57, 37.92s/it]
 66%|██████▌   | 93/141 [59:20<30:56, 38.68s/it]
 67%|██████▋   | 94/141 [59:45<27:03, 34.54s/it]{'loss': '1.423', 'grad_norm': '3.889', 'learning_rate': '0.0001524', 'epoch': '1.064'}


  0%|          | 0/134 [00:00<?, ?it/s][A

  1%|▏         | 2/134 [00:00<00:31,  4.13it/s][A

  2%|▏         | 3/134 [00:00<00:46,  2.81it/s][A

  3%|▎         | 4/134 [00:01<00:53,  2.42it/s][A

  4%|▎         | 5/134 [00:02<00:57,  2.25it/s][A

  4%|▍         | 6/134 [00:02<00:57,  2.21it/s][A

  5%|▌         | 7/134 [00:02<00:58,  2.19it/s][A

  6%|▌         | 8/134 [00:03<00:58,  2.17it/s][A

  7%|▋         | 9/134 [00:03<01:01,  2.04it/s][A

  7%|▋         | 10/134 [00:04<01:04,  1.92it/s][A

  8%|▊         | 11/134 [00:05<01:05,  1.88it/s][A

  9%|▉         | 12/134 [00:05<01:07,  1.81it/s][A

 10%|▉         | 13/134 [00:06<01:04,  1.86it/s][A

 10%|█         | 14/134 [00:06<01:04,  1.85it/s][A

 11%|█         | 15/134 [00:07<01:06,  1.80it/s][A

 12%|█▏        | 16/134 [00:07<01:04,  1.84it/s][A

 13%|█▎        | 17/134 [00:08<01:02,  1.87it/s][A

 13%|█▎        | 18/134 [00:08<01:00,  1.91it/s][A

 14%|█▍        | 19/134 [00:09<00:59,  1.95it/s][A

 15%|█▍        | 20/134 [00:09<01:00,  1.88it/s][A

 16%|█▌        | 21/134 [00:10<01:03,  1.77it/s][A

 16%|█▋        | 22/134 [00:11<01:04,  1.74it/s][A

 17%|█▋        | 23/134 [00:11<01:03,  1.75it/s][A

 18%|█▊        | 24/134 [00:12<01:03,  1.73it/s][A

 19%|█▊        | 25/134 [00:12<01:00,  1.80it/s][A

 19%|█▉        | 26/134 [00:13<01:00,  1.80it/s][A

 20%|██        | 27/134 [00:14<01:02,  1.72it/s][A

 21%|██        | 28/134 [00:14<01:03,  1.66it/s][A

 22%|██▏       | 29/134 [00:15<01:05,  1.61it/s][A

 22%|██▏       | 30/134 [00:15<01:05,  1.60it/s][A

 23%|██▎       | 31/134 [00:16<01:04,  1.59it/s][A

 24%|██▍       | 32/134 [00:17<01:04,  1.59it/s][A

 25%|██▍       | 33/134 [00:17<01:04,  1.58it/s][A

 25%|██▌       | 34/134 [00:18<01:04,  1.55it/s][A

 26%|██▌       | 35/134 [00:19<01:04,  1.54it/s][A

 27%|██▋       | 36/134 [00:19<01:04,  1.53it/s][A

 28%|██▊       | 37/134 [00:20<01:03,  1.52it/s][A

 28%|██▊       | 38/134 [00:21<01:03,  1.52it/s][A

 29%|██▉       | 39/134 [00:21<01:02,  1.51it/s][A

 30%|██▉       | 40/134 [00:22<01:01,  1.53it/s][A

 31%|███       | 41/134 [00:23<01:01,  1.52it/s][A

 31%|███▏      | 42/134 [00:23<01:00,  1.52it/s][A

 32%|███▏      | 43/134 [00:24<00:59,  1.53it/s][A

 33%|███▎      | 44/134 [00:25<00:58,  1.53it/s][A

 34%|███▎      | 45/134 [00:25<00:58,  1.53it/s][A

 34%|███▍      | 46/134 [00:26<00:57,  1.53it/s][A

 35%|███▌      | 47/134 [00:27<00:56,  1.53it/s][A

 36%|███▌      | 48/134 [00:27<00:56,  1.52it/s][A

 37%|███▋      | 49/134 [00:28<00:54,  1.56it/s][A

 37%|███▋      | 50/134 [00:28<00:52,  1.61it/s][A

 38%|███▊      | 51/134 [00:29<00:52,  1.58it/s][A

 39%|███▉      | 52/134 [00:30<00:52,  1.57it/s][A

 40%|███▉      | 53/134 [00:30<00:51,  1.57it/s][A

 40%|████      | 54/134 [00:31<00:51,  1.55it/s][A

 41%|████      | 55/134 [00:32<00:51,  1.54it/s][A

 42%|████▏     | 56/134 [00:32<00:51,  1.53it/s][A

 43%|████▎     | 57/134 [00:33<00:50,  1.52it/s][A

 43%|████▎     | 58/134 [00:34<00:49,  1.52it/s][A

 44%|████▍     | 59/134 [00:34<00:49,  1.52it/s][A

 45%|████▍     | 60/134 [00:35<00:47,  1.55it/s][A

 46%|████▌     | 61/134 [00:36<00:47,  1.54it/s][A

 46%|████▋     | 62/134 [00:36<00:47,  1.52it/s][A

 47%|████▋     | 63/134 [00:37<00:45,  1.55it/s][A

 48%|████▊     | 64/134 [00:38<00:45,  1.55it/s][A

 49%|████▊     | 65/134 [00:38<00:44,  1.54it/s][A

 49%|████▉     | 66/134 [00:39<00:42,  1.59it/s][A

 50%|█████     | 67/134 [00:39<00:39,  1.69it/s][A

 51%|█████     | 68/134 [00:40<00:37,  1.76it/s][A

 51%|█████▏    | 69/134 [00:40<00:37,  1.75it/s][A

 52%|█████▏    | 70/134 [00:41<00:37,  1.72it/s][A

 53%|█████▎    | 71/134 [00:42<00:35,  1.78it/s][A

 54%|█████▎    | 72/134 [00:42<00:33,  1.83it/s][A

 54%|█████▍    | 73/134 [00:43<00:33,  1.81it/s][A

 55%|█████▌    | 74/134 [00:43<00:34,  1.76it/s][A

 56%|█████▌    | 75/134 [00:44<00:32,  1.81it/s][A

 57%|█████▋    | 76/134 [00:44<00:31,  1.85it/s][A

 57%|█████▋    | 77/134 [00:45<00:30,  1.88it/s][A

 58%|█████▊    | 78/134 [00:45<00:30,  1.86it/s][A

 59%|█████▉    | 79/134 [00:46<00:30,  1.83it/s][A

 60%|█████▉    | 80/134 [00:46<00:28,  1.90it/s][A

 60%|██████    | 81/134 [00:47<00:27,  1.92it/s][A

 61%|██████    | 82/134 [00:47<00:27,  1.91it/s][A

 62%|██████▏   | 83/134 [00:48<00:26,  1.92it/s][A

 63%|██████▎   | 84/134 [00:48<00:25,  1.95it/s][A

 63%|██████▎   | 85/134 [00:49<00:25,  1.91it/s][A

 64%|██████▍   | 86/134 [00:50<00:26,  1.83it/s][A

 65%|██████▍   | 87/134 [00:50<00:25,  1.81it/s][A

 66%|██████▌   | 88/134 [00:51<00:25,  1.77it/s][A

 66%|██████▋   | 89/134 [00:51<00:24,  1.83it/s][A

 67%|██████▋   | 90/134 [00:52<00:23,  1.88it/s][A

 68%|██████▊   | 91/134 [00:52<00:22,  1.92it/s][A

 69%|██████▊   | 92/134 [00:53<00:21,  1.94it/s][A

 69%|██████▉   | 93/134 [00:53<00:20,  1.96it/s][A

 70%|███████   | 94/134 [00:54<00:20,  1.97it/s][A

 71%|███████   | 95/134 [00:54<00:19,  2.00it/s][A

 72%|███████▏  | 96/134 [00:55<00:19,  1.99it/s][A

 72%|███████▏  | 97/134 [00:55<00:18,  2.00it/s][A

 73%|███████▎  | 98/134 [00:56<00:18,  1.91it/s][A

 74%|███████▍  | 99/134 [00:56<00:19,  1.82it/s][A

 75%|███████▍  | 100/134 [00:57<00:18,  1.87it/s][A

 75%|███████▌  | 101/134 [00:57<00:17,  1.89it/s][A

 76%|███████▌  | 102/134 [00:58<00:16,  1.91it/s][A

 77%|███████▋  | 103/134 [00:58<00:16,  1.93it/s][A

 78%|███████▊  | 104/134 [00:59<00:15,  1.98it/s][A

 78%|███████▊  | 105/134 [00:59<00:14,  2.00it/s][A

 79%|███████▉  | 106/134 [01:00<00:14,  1.90it/s][A

 80%|███████▉  | 107/134 [01:01<00:14,  1.82it/s][A

 81%|████████  | 108/134 [01:01<00:13,  1.87it/s][A

 81%|████████▏ | 109/134 [01:02<00:13,  1.92it/s][A

 82%|████████▏ | 110/134 [01:02<00:12,  1.92it/s][A

 83%|████████▎ | 111/134 [01:03<00:11,  1.94it/s][A

 84%|████████▎ | 112/134 [01:03<00:11,  1.95it/s][A

 84%|████████▍ | 113/134 [01:04<00:10,  1.97it/s][A

 85%|████████▌ | 114/134 [01:04<00:09,  2.02it/s][A

 86%|████████▌ | 115/134 [01:05<00:09,  2.06it/s][A

 87%|████████▋ | 116/134 [01:05<00:08,  2.01it/s][A

 87%|████████▋ | 117/134 [01:06<00:08,  1.93it/s][A

 88%|████████▊ | 118/134 [01:06<00:08,  1.97it/s][A

 89%|████████▉ | 119/134 [01:07<00:07,  1.88it/s][A

 90%|████████▉ | 120/134 [01:07<00:07,  1.81it/s][A

 90%|█████████ | 121/134 [01:08<00:07,  1.83it/s][A

 91%|█████████ | 122/134 [01:08<00:06,  1.87it/s][A

 92%|█████████▏| 123/134 [01:09<00:05,  1.89it/s][A

 93%|█████████▎| 124/134 [01:09<00:05,  1.95it/s][A

 93%|█████████▎| 125/134 [01:10<00:04,  1.96it/s][A

 94%|█████████▍| 126/134 [01:10<00:04,  1.96it/s][A

 95%|█████████▍| 127/134 [01:11<00:03,  1.88it/s][A

 96%|█████████▌| 128/134 [01:11<00:03,  1.83it/s][A

 96%|█████████▋| 129/134 [01:12<00:02,  1.81it/s][A

 97%|█████████▋| 130/134 [01:13<00:02,  1.78it/s][A

 98%|█████████▊| 131/134 [01:13<00:01,  1.80it/s][A

 99%|█████████▊| 132/134 [01:14<00:01,  1.78it/s][A

 99%|█████████▉| 133/134 [01:14<00:00,  1.79it/s][A

100%|██████████| 134/134 [01:15<00:00,  1.75it/s][A
                                                


                                                 
[A
 67%|██████▋   | 94/141 [1:01:00<27:03, 34.54s/it]

100%|██████████| 134/134 [01:15<00:00,  1.75it/s][A

                                                 [A{'eval_loss': 'nan', 'eval_runtime': '75.91', 'eval_samples_per_second': '3.531', 'eval_steps_per_second': '1.765', 'epoch': '2'}


Writing model shards:   0%|          | 0/1 [00:00<?, ?it/s][A

Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.57s/it][A
Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.57s/it]
/home/users/jchoudhari/argument-aware-rag/.venv/lib/python3.10/site-packages/torch/utils/checkpoint.py:1399: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
  with device_autocast_ctx, torch.cpu.amp.autocast(**cpu_autocast_kwargs), recompute_context:  # type: ignore[attr-defined]

 67%|██████▋   | 95/141 [1:01:47<46:42, 60.93s/it]
 68%|██████▊   | 96/141 [1:02:24<40:23, 53.86s/it]
 69%|██████▉   | 97/141 [1:03:02<35:56, 49.02s/it]
 70%|██████▉   | 98/141 [1:03:37<31:59, 44.65s/it]
 70%|███████   | 99/141 [1:04:13<29:36, 42.29s/it]
 71%|███████   | 100/141 [1:04:54<28:31, 41.74s/it]
                                                   

 71%|███████   | 100/141 [1:04:54<28:31, 41.74s/it]
 72%|███████▏  | 101/141 [1:05:31<26:58, 40.46s/it]
 72%|███████▏  | 102/141 [1:06:10<25:55, 39.90s/it]
 73%|███████▎  | 103/141 [1:06:48<24:56, 39.38s/it]
 74%|███████▍  | 104/141 [1:07:26<23:55, 38.81s/it]
 74%|███████▍  | 105/141 [1:08:04<23:11, 38.66s/it]
 75%|███████▌  | 106/141 [1:08:40<22:04, 37.86s/it]
 76%|███████▌  | 107/141 [1:09:18<21:25, 37.81s/it]
 77%|███████▋  | 108/141 [1:09:53<20:28, 37.22s/it]
 77%|███████▋  | 109/141 [1:10:29<19:32, 36.63s/it]
 78%|███████▊  | 110/141 [1:11:05<18:52, 36.52s/it]
 79%|███████▊  | 111/141 [1:11:40<18:04, 36.15s/it]
 79%|███████▉  | 112/141 [1:12:19<17:52, 36.99s/it]
 80%|████████  | 113/141 [1:13:00<17:47, 38.13s/it]
 81%|████████  | 114/141 [1:13:39<17:16, 38.38s/it]
 82%|████████▏ | 115/141 [1:14:17<16:38, 38.40s/it]
 82%|████████▏ | 116/141 [1:14:56<16:04, 38.58s/it]
 83%|████████▎ | 117/141 [1:15:33<15:12, 38.00s/it]
 84%|████████▎ | 118/141 [1:16:12<14:43, 38.39s/it]
 84%|████████▍ | 119/141 [1:16:51<14:04, 38.37s/it]
 85%|████████▌ | 120/141 [1:17:29<13:26, 38.39s/it]
 86%|████████▌ | 121/141 [1:18:09<12:54, 38.71s/it]
 87%|████████▋ | 122/141 [1:18:46<12:09, 38.39s/it]
 87%|████████▋ | 123/141 [1:19:26<11:36, 38.69s/it]
 88%|████████▊ | 124/141 [1:20:03<10:53, 38.42s/it]
 89%|████████▊ | 125/141 [1:20:40<10:04, 37.79s/it]
 89%|████████▉ | 126/141 [1:21:20<09:38, 38.58s/it]
 90%|█████████ | 127/141 [1:21:59<09:00, 38.57s/it]
 91%|█████████ | 128/141 [1:22:36<08:17, 38.30s/it]
 91%|█████████▏| 129/141 [1:23:13<07:33, 37.81s/it]
 92%|█████████▏| 130/141 [1:23:51<06:57, 37.99s/it]
 93%|█████████▎| 131/141 [1:24:29<06:19, 37.99s/it]
 94%|█████████▎| 132/141 [1:25:06<05:39, 37.71s/it]
 94%|█████████▍| 133/141 [1:25:44<05:00, 37.52s/it]
 95%|█████████▌| 134/141 [1:26:19<04:17, 36.79s/it]
 96%|█████████▌| 135/141 [1:26:56<03:42, 37.03s/it]
 96%|█████████▋| 136/141 [1:27:34<03:06, 37.21s/it]
 97%|█████████▋| 137/141 [1:28:10<02:27, 36.94s/it]
 98%|█████████▊| 138/141 [1:28:50<01:53, 37.75s/it]
 99%|█████████▊| 139/141 [1:29:27<01:15, 37.51s/it]
 99%|█████████▉| 140/141 [1:30:03<00:37, 37.25s/it]
100%|██████████| 141/141 [1:30:27<00:00, 33.22s/it]{'loss': '0.255', 'grad_norm': '0.6317', 'learning_rate': '7.302e-05', 'epoch': '2.129'}


  0%|          | 0/134 [00:00<?, ?it/s][A

  1%|▏         | 2/134 [00:00<00:31,  4.21it/s][A

  2%|▏         | 3/134 [00:00<00:45,  2.89it/s][A

  3%|▎         | 4/134 [00:01<00:52,  2.47it/s][A

  4%|▎         | 5/134 [00:01<00:56,  2.30it/s][A

  4%|▍         | 6/134 [00:02<00:57,  2.24it/s][A

  5%|▌         | 7/134 [00:02<00:57,  2.20it/s][A

  6%|▌         | 8/134 [00:03<00:58,  2.14it/s][A

  7%|▋         | 9/134 [00:03<01:02,  1.99it/s][A

  7%|▋         | 10/134 [00:04<01:05,  1.88it/s][A

  8%|▊         | 11/134 [00:05<01:06,  1.84it/s][A

  9%|▉         | 12/134 [00:05<01:07,  1.80it/s][A

 10%|▉         | 13/134 [00:06<01:05,  1.83it/s][A

 10%|█         | 14/134 [00:06<01:06,  1.80it/s][A

 11%|█         | 15/134 [00:07<01:07,  1.76it/s][A

 12%|█▏        | 16/134 [00:07<01:04,  1.82it/s][A

 13%|█▎        | 17/134 [00:08<01:03,  1.85it/s][A

 13%|█▎        | 18/134 [00:08<01:01,  1.90it/s][A

 14%|█▍        | 19/134 [00:09<00:59,  1.93it/s][A

 15%|█▍        | 20/134 [00:10<01:00,  1.89it/s][A

 16%|█▌        | 21/134 [00:10<01:04,  1.75it/s][A

 16%|█▋        | 22/134 [00:11<01:05,  1.71it/s][A

 17%|█▋        | 23/134 [00:11<01:05,  1.71it/s][A

 18%|█▊        | 24/134 [00:12<01:04,  1.70it/s][A

 19%|█▊        | 25/134 [00:13<01:02,  1.75it/s][A

 19%|█▉        | 26/134 [00:13<01:02,  1.74it/s][A

 20%|██        | 27/134 [00:14<01:04,  1.66it/s][A

 21%|██        | 28/134 [00:14<01:05,  1.61it/s][A

 22%|██▏       | 29/134 [00:15<01:06,  1.58it/s][A

 22%|██▏       | 30/134 [00:16<01:07,  1.55it/s][A

 23%|██▎       | 31/134 [00:16<01:07,  1.54it/s][A

 24%|██▍       | 32/134 [00:17<01:06,  1.53it/s][A

 25%|██▍       | 33/134 [00:18<01:05,  1.53it/s][A

 25%|██▌       | 34/134 [00:18<01:05,  1.54it/s][A

 26%|██▌       | 35/134 [00:19<01:04,  1.53it/s][A

 27%|██▋       | 36/134 [00:20<01:04,  1.53it/s][A

 28%|██▊       | 37/134 [00:20<01:03,  1.53it/s][A

 28%|██▊       | 38/134 [00:21<01:03,  1.52it/s][A

 29%|██▉       | 39/134 [00:22<01:02,  1.53it/s][A

 30%|██▉       | 40/134 [00:22<01:01,  1.54it/s][A

 31%|███       | 41/134 [00:23<01:00,  1.54it/s][A

 31%|███▏      | 42/134 [00:24<00:59,  1.54it/s][A

 32%|███▏      | 43/134 [00:24<00:59,  1.54it/s][A

 33%|███▎      | 44/134 [00:25<00:58,  1.53it/s][A

 34%|███▎      | 45/134 [00:26<00:58,  1.52it/s][A

 34%|███▍      | 46/134 [00:26<00:58,  1.51it/s][A

 35%|███▌      | 47/134 [00:27<00:57,  1.52it/s][A

 36%|███▌      | 48/134 [00:28<00:56,  1.52it/s][A

 37%|███▋      | 49/134 [00:28<00:54,  1.56it/s][A

 37%|███▋      | 50/134 [00:29<00:52,  1.60it/s][A

 38%|███▊      | 51/134 [00:29<00:52,  1.58it/s][A

 39%|███▉      | 52/134 [00:30<00:52,  1.56it/s][A

 40%|███▉      | 53/134 [00:31<00:51,  1.56it/s][A

 40%|████      | 54/134 [00:31<00:51,  1.56it/s][A

 41%|████      | 55/134 [00:32<00:51,  1.54it/s][A

 42%|████▏     | 56/134 [00:33<00:50,  1.53it/s][A

 43%|████▎     | 57/134 [00:33<00:50,  1.53it/s][A

 43%|████▎     | 58/134 [00:34<00:49,  1.52it/s][A

 44%|████▍     | 59/134 [00:35<00:49,  1.52it/s][A

 45%|████▍     | 60/134 [00:35<00:48,  1.52it/s][A

 46%|████▌     | 61/134 [00:36<00:47,  1.54it/s][A

 46%|████▋     | 62/134 [00:37<00:46,  1.54it/s][A

 47%|████▋     | 63/134 [00:37<00:46,  1.53it/s][A

 48%|████▊     | 64/134 [00:38<00:45,  1.53it/s][A

 49%|████▊     | 65/134 [00:39<00:45,  1.52it/s][A

 49%|████▉     | 66/134 [00:39<00:43,  1.57it/s][A

 50%|█████     | 67/134 [00:40<00:39,  1.68it/s][A

 51%|█████     | 68/134 [00:40<00:37,  1.77it/s][A

 51%|█████▏    | 69/134 [00:41<00:36,  1.79it/s][A

 52%|█████▏    | 70/134 [00:41<00:36,  1.76it/s][A

 53%|█████▎    | 71/134 [00:42<00:34,  1.80it/s][A

 54%|█████▎    | 72/134 [00:42<00:33,  1.83it/s][A

 54%|█████▍    | 73/134 [00:43<00:33,  1.82it/s][A

 55%|█████▌    | 74/134 [00:43<00:33,  1.78it/s][A

 56%|█████▌    | 75/134 [00:44<00:32,  1.84it/s][A

 57%|█████▋    | 76/134 [00:45<00:31,  1.87it/s][A

 57%|█████▋    | 77/134 [00:45<00:30,  1.89it/s][A

 58%|█████▊    | 78/134 [00:46<00:29,  1.87it/s][A

 59%|█████▉    | 79/134 [00:46<00:30,  1.81it/s][A

 60%|█████▉    | 80/134 [00:47<00:28,  1.87it/s][A

 60%|██████    | 81/134 [00:47<00:27,  1.91it/s][A

 61%|██████    | 82/134 [00:48<00:27,  1.92it/s][A

 62%|██████▏   | 83/134 [00:48<00:26,  1.92it/s][A

 63%|██████▎   | 84/134 [00:49<00:25,  1.94it/s][A

 63%|██████▎   | 85/134 [00:49<00:26,  1.86it/s][A

 64%|██████▍   | 86/134 [00:50<00:26,  1.79it/s][A

 65%|██████▍   | 87/134 [00:50<00:26,  1.77it/s][A

 66%|██████▌   | 88/134 [00:51<00:26,  1.75it/s][A

 66%|██████▋   | 89/134 [00:52<00:24,  1.82it/s][A

 67%|██████▋   | 90/134 [00:52<00:23,  1.85it/s][A

 68%|██████▊   | 91/134 [00:53<00:22,  1.88it/s][A

 69%|██████▊   | 92/134 [00:53<00:21,  1.91it/s][A

 69%|██████▉   | 93/134 [00:54<00:21,  1.92it/s][A

 70%|███████   | 94/134 [00:54<00:20,  1.93it/s][A

 71%|███████   | 95/134 [00:55<00:19,  1.95it/s][A

 72%|███████▏  | 96/134 [00:55<00:19,  1.96it/s][A

 72%|███████▏  | 97/134 [00:56<00:18,  1.96it/s][A

 73%|███████▎  | 98/134 [00:56<00:19,  1.88it/s][A

 74%|███████▍  | 99/134 [00:57<00:19,  1.81it/s][A

 75%|███████▍  | 100/134 [00:57<00:18,  1.85it/s][A

 75%|███████▌  | 101/134 [00:58<00:17,  1.89it/s][A

 76%|███████▌  | 102/134 [00:58<00:16,  1.91it/s][A

 77%|███████▋  | 103/134 [00:59<00:16,  1.92it/s][A

 78%|███████▊  | 104/134 [00:59<00:15,  1.94it/s][A

 78%|███████▊  | 105/134 [01:00<00:14,  2.00it/s][A

 79%|███████▉  | 106/134 [01:00<00:14,  1.98it/s][A

 80%|███████▉  | 107/134 [01:01<00:14,  1.89it/s][A

 81%|████████  | 108/134 [01:01<00:13,  1.93it/s][A

 81%|████████▏ | 109/134 [01:02<00:12,  1.97it/s][A

 82%|████████▏ | 110/134 [01:02<00:12,  1.97it/s][A

 83%|████████▎ | 111/134 [01:03<00:11,  1.99it/s][A

 84%|████████▎ | 112/134 [01:03<00:11,  1.98it/s][A

 84%|████████▍ | 113/134 [01:04<00:10,  1.98it/s][A

 85%|████████▌ | 114/134 [01:04<00:10,  1.97it/s][A

 86%|████████▌ | 115/134 [01:05<00:09,  2.00it/s][A

 87%|████████▋ | 116/134 [01:05<00:09,  1.91it/s][A

 87%|████████▋ | 117/134 [01:06<00:09,  1.84it/s][A

 88%|████████▊ | 118/134 [01:07<00:08,  1.89it/s][A

 89%|████████▉ | 119/134 [01:07<00:08,  1.83it/s][A

 90%|████████▉ | 120/134 [01:08<00:07,  1.79it/s][A

 90%|█████████ | 121/134 [01:08<00:07,  1.84it/s][A

 91%|█████████ | 122/134 [01:09<00:06,  1.89it/s][A

 92%|█████████▏| 123/134 [01:09<00:05,  1.94it/s][A

 93%|█████████▎| 124/134 [01:10<00:05,  1.96it/s][A

 93%|█████████▎| 125/134 [01:10<00:04,  1.99it/s][A

 94%|█████████▍| 126/134 [01:11<00:03,  2.00it/s][A

 95%|█████████▍| 127/134 [01:11<00:03,  1.93it/s][A

 96%|█████████▌| 128/134 [01:12<00:03,  1.85it/s][A

 96%|█████████▋| 129/134 [01:12<00:02,  1.83it/s][A

 97%|█████████▋| 130/134 [01:13<00:02,  1.77it/s][A

 98%|█████████▊| 131/134 [01:14<00:01,  1.77it/s][A

 99%|█████████▊| 132/134 [01:14<00:01,  1.75it/s][A

 99%|█████████▉| 133/134 [01:15<00:00,  1.78it/s][A

100%|██████████| 134/134 [01:15<00:00,  1.77it/s][A
                                                   


                                                 
[A
100%|██████████| 141/141 [1:31:43<00:00, 33.22s/it]

100%|██████████| 134/134 [01:16<00:00,  1.77it/s][A

                                                 [A{'eval_loss': 'nan', 'eval_runtime': '76.28', 'eval_samples_per_second': '3.513', 'eval_steps_per_second': '1.757', 'epoch': '3'}


Writing model shards:   0%|          | 0/1 [00:00<?, ?it/s][A

Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.68s/it][A
Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.69s/it]

                                                   

100%|██████████| 141/141 [1:31:50<00:00, 33.22s/it]
100%|██████████| 141/141 [1:31:50<00:00, 39.08s/it]
{'train_runtime': '5511', 'train_samples_per_second': '0.813', 'train_steps_per_second': '0.026', 'train_loss': '0.615', 'epoch': '3'}

Writing model shards:   0%|          | 0/1 [00:00<?, ?it/s]
Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.53s/it]
Writing model shards: 100%|██████████| 1/1 [00:05<00:00,  5.53s/it]
[train-β] saved student to phase2_student_beta_qwen0.5b