submission_id: undi95-meta-llama-3-70b_6209_v22
developer_uid: chai_backend_admin
alignment_samples: 0
best_of: 2
celo_rating: 1211.42
display_name: undi95-meta-llama-3-3k
formatter: {'memory_template': "<|im_start|>system\n{bot_name}'s Persona: {memory}<|im_end|>\n", 'prompt_template': '<|im_start|>system\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 50, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|im_end|>', '<|im_start|>', '\n\n'], 'max_input_tokens': 3000, 'best_of': 2, 'max_output_tokens': 64}
is_internal_developer: True
language_model: Undi95/Meta-Llama-3-70B-Instruct-hf
max_input_tokens: 3000
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Undi95/Meta-Llama-3-70B-
model_name: undi95-meta-llama-3-3k
model_num_parameters: 70553706496.0
model_repo: Undi95/Meta-Llama-3-70B-Instruct-hf
model_size: 71B
num_battles: 20334
num_wins: 10335
propriety_score: 0.7386412808308092
propriety_total_count: 2311.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "''", 'prompt_template': "''", 'response_template': '{bot_name}:', 'truncate_by_message': False, 'user_template': '{user_name}: {message}\n'}
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-23T04:14:32+00:00
us_pacific_date: 2024-07-22
win_ratio: 0.508262024195928
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-meta-llama-3-70b-6209-v22-mkmlizer
Waiting for job on undi95-meta-llama-3-70b-6209-v22-mkmlizer to finish
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v45: ('http://chaiml-sao10k-l3-rp-v3-3-v45-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ _____ __ __ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ /___/ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ Version: 0.9.5.post3 ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ https://mk1.ai ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ belonging to: ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ Chai Research Corp. ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Downloaded to shared memory in 263.708s
undi95-meta-llama-3-70b-6209-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0o7bwa51, device:0
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission cycy233-l3-bc-v0-c1_v5: ('http://cycy233-l3-bc-v0-c1-v5-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:35670->127.0.0.1:8080: read: connection reset by peer\n')
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 1%| | 4/723 [00:00<00:23, 30.60it/s] Loading 0: 1%| | 9/723 [00:00<00:18, 39.08it/s] Loading 0: 2%|▏ | 14/723 [00:00<00:16, 42.35it/s] Loading 0: 3%|▎ | 19/723 [00:00<00:28, 24.89it/s] Loading 0: 3%|▎ | 23/723 [00:00<00:29, 23.45it/s] Loading 0: 4%|▍ | 30/723 [00:00<00:21, 32.64it/s] Loading 0: 5%|▍ | 35/723 [00:01<00:21, 32.56it/s] Loading 0: 6%|▌ | 42/723 [00:01<00:21, 31.20it/s] Loading 0: 6%|▋ | 46/723 [00:01<00:24, 27.64it/s] Loading 0: 7%|▋ | 50/723 [00:01<00:26, 25.53it/s] Loading 0: 8%|▊ | 57/723 [00:01<00:19, 33.31it/s] Loading 0: 8%|▊ | 61/723 [00:01<00:20, 32.29it/s] Loading 0: 9%|▉ | 68/723 [00:02<00:20, 31.25it/s] Loading 0: 10%|▉ | 72/723 [00:02<00:23, 27.70it/s] Loading 0: 11%|█ | 76/723 [00:02<00:23, 27.68it/s] Loading 0: 11%|█ | 81/723 [00:02<00:20, 31.63it/s] Loading 0: 12%|█▏ | 85/723 [00:02<00:20, 31.33it/s] Loading 0: 12%|█▏ | 90/723 [00:02<00:18, 34.91it/s] Loading 0: 13%|█▎ | 94/723 [00:03<00:26, 23.68it/s] Loading 0: 14%|█▎ | 99/723 [00:03<00:22, 28.07it/s] Loading 0: 14%|█▍ | 103/723 [00:03<00:21, 28.74it/s] Loading 0: 15%|█▍ | 108/723 [00:03<00:18, 32.74it/s] Loading 0: 15%|█▌ | 112/723 [00:03<00:19, 31.76it/s] Loading 0: 16%|█▌ | 116/723 [00:03<00:22, 26.82it/s] Loading 0: 17%|█▋ | 120/723 [00:04<00:21, 27.94it/s] Loading 0: 17%|█▋ | 124/723 [00:04<00:21, 28.31it/s] Loading 0: 18%|█▊ | 128/723 [00:18<10:46, 1.09s/it] Loading 0: 18%|█▊ | 130/723 [00:18<08:59, 1.10it/s] Loading 0: 19%|█▊ | 135/723 [00:18<05:35, 1.75it/s] Loading 0: 19%|█▉ | 140/723 [00:19<03:39, 2.65it/s] Loading 0: 20%|█▉ | 144/723 [00:19<02:48, 3.43it/s] Loading 0: 20%|██ | 148/723 [00:19<02:04, 4.63it/s] Loading 0: 21%|██ | 153/723 [00:19<01:25, 6.69it/s] Loading 0: 22%|██▏ | 157/723 [00:19<01:05, 8.58it/s] Loading 0: 22%|██▏ | 162/723 [00:19<00:47, 11.80it/s] Loading 0: 23%|██▎ | 168/723 [00:20<00:36, 15.02it/s] Loading 0: 24%|██▍ | 172/723 [00:20<00:34, 16.17it/s] Loading 0: 24%|██▍ | 176/723 [00:20<00:31, 17.27it/s] Loading 0: 25%|██▌ | 183/723 [00:20<00:22, 24.52it/s] Loading 0: 26%|██▌ | 187/723 [00:20<00:20, 25.60it/s] Loading 0: 27%|██▋ | 194/723 [00:20<00:19, 27.24it/s] Loading 0: 27%|██▋ | 198/723 [00:21<00:20, 25.32it/s] Loading 0: 28%|██▊ | 202/723 [00:21<00:20, 25.97it/s] Loading 0: 29%|██▊ | 207/723 [00:21<00:17, 30.20it/s] Loading 0: 29%|██▉ | 211/723 [00:21<00:16, 30.46it/s] Loading 0: 30%|██▉ | 216/723 [00:21<00:14, 34.32it/s] Loading 0: 30%|███ | 220/723 [00:21<00:20, 24.07it/s] Loading 0: 31%|███ | 225/723 [00:22<00:17, 28.55it/s] Loading 0: 32%|███▏ | 229/723 [00:22<00:16, 29.15it/s] Loading 0: 32%|███▏ | 234/723 [00:22<00:14, 33.16it/s] Loading 0: 33%|███▎ | 238/723 [00:22<00:15, 32.10it/s] Loading 0: 33%|███▎ | 242/723 [00:22<00:17, 27.13it/s] Loading 0: 34%|███▍ | 246/723 [00:22<00:16, 28.15it/s] Loading 0: 35%|███▍ | 250/723 [00:22<00:16, 28.58it/s] Loading 0: 35%|███▌ | 255/723 [00:22<00:14, 33.39it/s] Loading 0: 36%|███▌ | 259/723 [00:23<00:14, 32.29it/s] Loading 0: 36%|███▋ | 263/723 [00:23<00:13, 34.13it/s] Loading 0: 37%|███▋ | 268/723 [00:23<00:15, 29.31it/s] Loading 0: 38%|███▊ | 272/723 [00:37<07:39, 1.02s/it] Loading 0: 38%|███▊ | 274/723 [00:37<06:26, 1.16it/s] Loading 0: 39%|███▊ | 279/723 [00:37<04:03, 1.82it/s] Loading 0: 39%|███▉ | 283/723 [00:38<02:53, 2.54it/s] Loading 0: 40%|███▉ | 288/723 [00:38<01:55, 3.78it/s] Loading 0: 41%|████ | 294/723 [00:38<01:17, 5.55it/s] Loading 0: 41%|████ | 298/723 [00:38<01:01, 6.86it/s] Loading 0: 42%|████▏ | 301/723 [00:38<00:51, 8.14it/s] Loading 0: 42%|████▏ | 306/723 [00:38<00:36, 11.38it/s] Loading 0: 43%|████▎ | 310/723 [00:38<00:29, 13.87it/s] Loading 0: 44%|████▎ | 315/723 [00:39<00:22, 18.16it/s] Loading 0: 44%|████▍ | 320/723 [00:39<00:20, 19.97it/s] Loading 0: 45%|████▍ | 324/723 [00:39<00:19, 20.08it/s] Loading 0: 45%|████▌ | 328/723 [00:39<00:18, 21.77it/s] Loading 0: 46%|████▌ | 333/723 [00:39<00:14, 26.41it/s] Loading 0: 47%|████▋ | 337/723 [00:39<00:14, 27.52it/s] Loading 0: 47%|████▋ | 342/723 [00:39<00:11, 31.85it/s] Loading 0: 48%|████▊ | 346/723 [00:40<00:16, 22.83it/s] Loading 0: 49%|████▊ | 351/723 [00:40<00:13, 27.53it/s] Loading 0: 49%|████▉ | 355/723 [00:40<00:12, 28.47it/s] Loading 0: 50%|████▉ | 360/723 [00:40<00:11, 32.57it/s] Loading 0: 50%|█████ | 364/723 [00:40<00:11, 31.74it/s] Loading 0: 51%|█████ | 368/723 [00:40<00:13, 27.24it/s] Loading 0: 51%|█████▏ | 372/723 [00:41<00:12, 28.18it/s] Loading 0: 52%|█████▏ | 376/723 [00:41<00:12, 28.67it/s] Loading 0: 53%|█████▎ | 382/723 [00:41<00:10, 31.40it/s] Loading 0: 54%|█████▎ | 387/723 [00:41<00:09, 35.03it/s] Loading 0: 54%|█████▍ | 392/723 [00:41<00:08, 38.04it/s] Loading 0: 55%|█████▍ | 396/723 [00:41<00:12, 25.86it/s] Loading 0: 55%|█████▌ | 400/723 [00:41<00:11, 27.15it/s] Loading 0: 56%|█████▌ | 404/723 [00:56<05:22, 1.01s/it] Loading 0: 57%|█████▋ | 409/723 [00:56<03:34, 1.46it/s] Loading 0: 57%|█████▋ | 414/723 [00:56<02:25, 2.13it/s] Loading 0: 58%|█████▊ | 420/723 [00:56<01:36, 3.16it/s] Loading 0: 59%|█████▊ | 424/723 [00:56<01:14, 4.01it/s] Loading 0: 59%|█████▉ | 427/723 [00:56<01:00, 4.88it/s] Loading 0: 60%|█████▉ | 432/723 [00:56<00:41, 6.99it/s] Loading 0: 60%|██████ | 436/723 [00:57<00:32, 8.91it/s] Loading 0: 61%|██████ | 441/723 [00:57<00:23, 12.19it/s] Loading 0: 62%|██████▏ | 446/723 [00:57<00:19, 14.57it/s] Loading 0: 62%|██████▏ | 450/723 [00:57<00:17, 15.81it/s] Loading 0: 63%|██████▎ | 454/723 [00:57<00:14, 17.98it/s] Loading 0: 63%|██████▎ | 459/723 [00:57<00:11, 22.60it/s] Loading 0: 64%|██████▍ | 463/723 [00:57<00:10, 24.49it/s] Loading 0: 65%|██████▍ | 468/723 [00:58<00:08, 29.09it/s] Loading 0: 65%|██████▌ | 472/723 [00:58<00:11, 21.96it/s] Loading 0: 66%|██████▌ | 477/723 [00:58<00:09, 26.60it/s] Loading 0: 67%|██████▋ | 481/723 [00:58<00:08, 27.69it/s] Loading 0: 67%|██████▋ | 486/723 [00:58<00:07, 32.05it/s] Loading 0: 68%|██████▊ | 490/723 [00:58<00:07, 31.39it/s] Loading 0: 68%|██████▊ | 494/723 [00:59<00:08, 27.04it/s] Loading 0: 69%|██████▉ | 498/723 [00:59<00:08, 28.02it/s] Loading 0: 69%|██████▉ | 502/723 [00:59<00:07, 28.52it/s] Loading 0: 70%|███████ | 507/723 [00:59<00:06, 33.26it/s] Loading 0: 71%|███████ | 511/723 [00:59<00:06, 32.20it/s] Loading 0: 71%|███████ | 515/723 [00:59<00:06, 34.10it/s] Loading 0: 72%|███████▏ | 520/723 [00:59<00:06, 29.46it/s] Loading 0: 72%|███████▏ | 524/723 [01:00<00:06, 29.55it/s] Loading 0: 73%|███████▎ | 528/723 [01:00<00:07, 26.45it/s] Loading 0: 74%|███████▍ | 534/723 [01:00<00:05, 33.37it/s] Loading 0: 74%|███████▍ | 538/723 [01:14<02:55, 1.06it/s] Loading 0: 76%|███████▌ | 546/723 [01:14<01:37, 1.81it/s] Loading 0: 76%|███████▌ | 550/723 [01:14<01:15, 2.30it/s] Loading 0: 77%|███████▋ | 554/723 [01:14<00:56, 2.97it/s] Loading 0: 78%|███████▊ | 561/723 [01:14<00:34, 4.71it/s] Loading 0: 78%|███████▊ | 565/723 [01:15<00:26, 5.89it/s] Loading 0: 79%|███████▉ | 572/723 [01:15<00:17, 8.41it/s] Loading 0: 80%|███████▉ | 576/723 [01:15<00:15, 9.73it/s] Loading 0: 80%|████████ | 580/723 [01:15<00:12, 11.61it/s] Loading 0: 81%|████████ | 585/723 [01:15<00:09, 15.15it/s] Loading 0: 81%|████████▏ | 589/723 [01:15<00:07, 17.52it/s] Loading 0: 82%|████████▏ | 594/723 [01:16<00:05, 21.83it/s] Loading 0: 83%|████████▎ | 598/723 [01:16<00:06, 18.30it/s] Loading 0: 83%|████████▎ | 603/723 [01:16<00:05, 22.78it/s] Loading 0: 84%|████████▍ | 607/723 [01:16<00:04, 24.38it/s] Loading 0: 85%|████████▍ | 612/723 [01:16<00:03, 28.87it/s] Loading 0: 85%|████████▌ | 616/723 [01:16<00:03, 28.98it/s] Loading 0: 86%|████████▌ | 620/723 [01:17<00:03, 25.79it/s] Loading 0: 86%|████████▋ | 624/723 [01:17<00:03, 27.15it/s] Loading 0: 87%|████████▋ | 628/723 [01:17<00:03, 27.92it/s] Loading 0: 88%|████████▊ | 633/723 [01:17<00:02, 32.80it/s] Loading 0: 88%|████████▊ | 637/723 [01:17<00:02, 31.94it/s] Loading 0: 89%|████████▊ | 641/723 [01:17<00:02, 33.89it/s] Loading 0: 89%|████████▉ | 646/723 [01:17<00:02, 29.70it/s] Loading 0: 90%|████████▉ | 650/723 [01:17<00:02, 29.96it/s] Loading 0: 90%|█████████ | 654/723 [01:18<00:02, 26.70it/s] Loading 0: 91%|█████████▏| 660/723 [01:18<00:01, 33.68it/s] Loading 0: 92%|█████████▏| 664/723 [01:18<00:01, 32.49it/s] Loading 0: 93%|█████████▎| 672/723 [01:18<00:01, 32.57it/s] Loading 0: 93%|█████████▎| 674/723 [01:32<00:01, 32.57it/s] Loading 0: 93%|█████████▎| 675/723 [01:32<00:43, 1.10it/s] Loading 0: 94%|█████████▍| 679/723 [01:32<00:29, 1.47it/s] Loading 0: 95%|█████████▍| 684/723 [01:33<00:18, 2.13it/s] Loading 0: 95%|█████████▌| 688/723 [01:33<00:12, 2.84it/s] Loading 0: 96%|█████████▌| 693/723 [01:33<00:07, 4.08it/s] Loading 0: 97%|█████████▋| 698/723 [01:33<00:04, 5.53it/s] Loading 0: 97%|█████████▋| 702/723 [01:33<00:03, 6.86it/s] Loading 0: 98%|█████████▊| 706/723 [01:33<00:01, 8.63it/s] Loading 0: 98%|█████████▊| 711/723 [01:33<00:01, 11.77it/s] Loading 0: 99%|█████████▉| 715/723 [01:34<00:00, 14.17it/s] Loading 0: 100%|█████████▉| 720/723 [01:34<00:00, 18.36it/s] Loading 0: 100%|█████████▉| 722/723 [01:44<00:00, 18.36it/s] Loading 0: 100%|██████████| 723/723 [01:44<00:00, 1.25it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
undi95-meta-llama-3-70b-6209-v22-mkmlizer: quantized model in 121.271s
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Processed model Undi95/Meta-Llama-3-70B-Instruct-hf in 384.979s
undi95-meta-llama-3-70b-6209-v22-mkmlizer: creating bucket guanaco-mkml-models
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-meta-llama-3-70b-6209-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/config.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/tokenizer.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/flywheel_model.5.safetensors
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/flywheel_model.0.safetensors
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/flywheel_model.1.safetensors
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/flywheel_model.4.safetensors
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/flywheel_model.3.safetensors
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v22/flywheel_model.2.safetensors
undi95-meta-llama-3-70b-6209-v22-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
undi95-meta-llama-3-70b-6209-v22-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-meta-llama-3-70b-6209-v22-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v22-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-meta-llama-3-70b-6209-v22-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v22-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:469: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
undi95-meta-llama-3-70b-6209-v22-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.17s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.77s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.98s/it]
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Saving duration: 1.334s
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.940s
undi95-meta-llama-3-70b-6209-v22-mkmlizer: creating bucket guanaco-reward-models
undi95-meta-llama-3-70b-6209-v22-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-meta-llama-3-70b-6209-v22-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/config.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/merges.txt
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/vocab.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/tokenizer.json
undi95-meta-llama-3-70b-6209-v22-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v22_reward/reward.tensors
Job undi95-meta-llama-3-70b-6209-v22-mkmlizer completed after 449.76s with status: succeeded
Stopping job with name undi95-meta-llama-3-70b-6209-v22-mkmlizer
Pipeline stage MKMLizer completed in 450.93s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service undi95-meta-llama-3-70b-6209-v22
Waiting for inference service undi95-meta-llama-3-70b-6209-v22 to be ready
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v46: ('http://chaiml-sao10k-l3-rp-v3-3-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Failed to get response for submission chaiml-sao10k-l3-rp-v3-3_v46: ('http://chaiml-sao10k-l3-rp-v3-3-v46-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
Inference service undi95-meta-llama-3-70b-6209-v22 ready after 141.7111234664917s
Pipeline stage ISVCDeployer completed in 143.46s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.321737051010132s
Received healthy response to inference request in 4.26099705696106s
Received healthy response to inference request in 4.186643362045288s
Received healthy response to inference request in 4.2836291790008545s
Received healthy response to inference request in 4.29801869392395s
5 requests
0 failed requests
5th percentile: 4.201514101028442
10th percentile: 4.216384840011597
20th percentile: 4.246126317977906
30th percentile: 4.265523481369018
40th percentile: 4.274576330184937
50th percentile: 4.2836291790008545
60th percentile: 4.289384984970093
70th percentile: 4.295140790939331
80th percentile: 4.502762365341186
90th percentile: 4.9122497081756595
95th percentile: 5.116993379592896
99th percentile: 5.280788316726684
mean time: 4.470205068588257
Pipeline stage StressChecker completed in 23.28s
undi95-meta-llama-3-70b_6209_v22 status is now deployed due to DeploymentManager action
undi95-meta-llama-3-70b_6209_v22 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-meta-llama-3-70b_6209_v22
Running pipeline stage ISVCDeleter
Checking if service undi95-meta-llama-3-70b-6209-v22 is running
Tearing down inference service undi95-meta-llama-3-70b-6209-v22
Service undi95-meta-llama-3-70b-6209-v22 has been torndown
Pipeline stage ISVCDeleter completed in 5.08s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-meta-llama-3-70b-6209-v22/config.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v22/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v22_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 12.28s
undi95-meta-llama-3-70b_6209_v22 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics