submission_id: undi95-meta-llama-3-70b_6209_v18
developer_uid: dzhao1
alignment_samples: 1923667
alignment_score: 3.4376035194685133
best_of: 2
celo_rating: 1191.89
display_name: undi95-meta-llama-3-70b_6209_v18
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': 512, 'best_of': 2, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Undi95/Meta-Llama-3-70B-Instruct-hf
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Undi95/Meta-Llama-3-70B-
model_name: undi95-meta-llama-3-70b_6209_v18
model_num_parameters: 70553706496.0
model_repo: Undi95/Meta-Llama-3-70B-Instruct-hf
model_size: 71B
num_battles: 5933025
num_wins: 2843386
propriety_score: 0.7390989063456365
propriety_total_count: 557123.0
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: 2024-07-19T16:39:39+00:00
us_pacific_date: 2024-07-19
win_ratio: 0.47924726425390085
Resubmit model
Running pipeline stage MKMLizer
Starting job with name undi95-meta-llama-3-70b-6209-v18-mkmlizer
Waiting for job on undi95-meta-llama-3-70b-6209-v18-mkmlizer to finish
Stopping job with name undi95-meta-llama-3-70b-6209-v18-mkmlizer
%s, retrying in %s seconds...
Starting job with name undi95-meta-llama-3-70b-6209-v18-mkmlizer
Waiting for job on undi95-meta-llama-3-70b-6209-v18-mkmlizer to finish
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ _____ __ __ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ /___/ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ Version: 0.9.5.post3 ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ https://mk1.ai ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ belonging to: ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ Chai Research Corp. ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission pawankrd-cosmosrp_v66: ('http://pawankrd-cosmosrp-v66-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:60922->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission arlineka-nyannyan_v3: ('http://arlineka-nyannyan-v3-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Downloaded to shared memory in 303.055s
undi95-meta-llama-3-70b-6209-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7dwmgwpz, device:0
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 0%| | 3/723 [00:00<00:34, 20.95it/s] Loading 0: 1%| | 6/723 [00:00<00:54, 13.08it/s] Loading 0: 1%| | 9/723 [00:00<00:41, 17.16it/s] Loading 0: 2%|▏ | 12/723 [00:00<00:43, 16.32it/s] Loading 0: 2%|▏ | 14/723 [00:00<00:41, 17.00it/s] Loading 0: 2%|▏ | 16/723 [00:01<00:46, 15.35it/s] Loading 0: 2%|▏ | 18/723 [00:01<00:59, 11.76it/s] Loading 0: 3%|▎ | 21/723 [00:01<00:49, 14.28it/s] Loading 0: 3%|▎ | 23/723 [00:01<01:01, 11.42it/s] Loading 0: 4%|▍ | 30/723 [00:01<00:38, 17.79it/s] Loading 0: 4%|▍ | 32/723 [00:02<00:49, 13.87it/s] Loading 0: 5%|▌ | 39/723 [00:02<00:31, 21.52it/s] Loading 0: 6%|▌ | 42/723 [00:02<00:33, 20.21it/s] Loading 0: 6%|▌ | 45/723 [00:02<00:49, 13.71it/s] Loading 0: 7%|▋ | 48/723 [00:03<00:47, 14.32it/s] Loading 0: 7%|▋ | 50/723 [00:03<00:58, 11.51it/s] Loading 0: 7%|▋ | 54/723 [00:03<00:43, 15.23it/s] Loading 0: 8%|▊ | 57/723 [00:03<00:43, 15.29it/s] Loading 0: 8%|▊ | 59/723 [00:04<01:00, 11.02it/s] Loading 0: 9%|▊ | 63/723 [00:04<00:43, 15.04it/s] Loading 0: 9%|▉ | 68/723 [00:04<00:35, 18.29it/s] Loading 0: 10%|▉ | 71/723 [00:04<00:57, 11.40it/s] Loading 0: 10%|█ | 75/723 [00:05<00:49, 13.16it/s] Loading 0: 11%|█ | 77/723 [00:05<01:02, 10.40it/s] Loading 0: 11%|█ | 81/723 [00:05<00:46, 13.81it/s] Loading 0: 12%|█▏ | 84/723 [00:05<00:44, 14.35it/s] Loading 0: 12%|█▏ | 86/723 [00:06<00:59, 10.71it/s] Loading 0: 12%|█▏ | 90/723 [00:06<00:43, 14.41it/s] Loading 0: 13%|█▎ | 93/723 [00:06<00:50, 12.40it/s] Loading 0: 13%|█▎ | 95/723 [00:07<01:04, 9.77it/s] Loading 0: 14%|█▎ | 99/723 [00:07<00:46, 13.45it/s] Loading 0: 14%|█▍ | 102/723 [00:07<00:44, 14.07it/s] Loading 0: 14%|█▍ | 104/723 [00:07<00:57, 10.78it/s] Loading 0: 15%|█▍ | 108/723 [00:07<00:41, 14.67it/s] Loading 0: 15%|█▌ | 111/723 [00:08<00:51, 11.85it/s] Loading 0: 16%|█▌ | 114/723 [00:08<00:43, 14.11it/s] Loading 0: 16%|█▌ | 116/723 [00:08<00:42, 14.39it/s] Loading 0: 16%|█▋ | 118/723 [00:08<00:45, 13.20it/s] Loading 0: 17%|█▋ | 120/723 [00:08<00:57, 10.41it/s] Loading 0: 17%|█▋ | 122/723 [00:09<01:33, 6.42it/s] Loading 0: 17%|█▋ | 124/723 [00:19<01:33, 6.42it/s] Loading 0: 17%|█▋ | 125/723 [00:24<19:25, 1.95s/it] Loading 0: 18%|█▊ | 129/723 [00:25<11:35, 1.17s/it] Loading 0: 18%|█▊ | 131/723 [00:25<09:15, 1.06it/s] Loading 0: 19%|█▉ | 136/723 [00:25<05:10, 1.89it/s] Loading 0: 19%|█▉ | 139/723 [00:25<03:53, 2.50it/s] Loading 0: 20%|█▉ | 142/723 [00:25<02:57, 3.27it/s] Loading 0: 20%|█▉ | 144/723 [00:26<02:37, 3.68it/s] Loading 0: 20%|██ | 147/723 [00:26<01:56, 4.97it/s] Loading 0: 21%|██ | 149/723 [00:26<01:47, 5.34it/s] Loading 0: 22%|██▏ | 156/723 [00:26<00:59, 9.53it/s] Loading 0: 22%|██▏ | 158/723 [00:27<01:03, 8.87it/s] Loading 0: 23%|██▎ | 165/723 [00:27<00:37, 15.08it/s] Loading 0: 23%|██▎ | 169/723 [00:27<00:39, 13.98it/s] Loading 0: 24%|██▍ | 172/723 [00:27<00:42, 12.91it/s] Loading 0: 24%|██▍ | 175/723 [00:28<00:44, 12.31it/s] Loading 0: 24%|██▍ | 177/723 [00:28<00:42, 12.76it/s] Loading 0: 25%|██▌ | 183/723 [00:28<00:31, 17.01it/s] Loading 0: 26%|██▌ | 186/723 [00:28<00:35, 15.14it/s] Loading 0: 27%|██▋ | 192/723 [00:28<00:25, 20.55it/s] Loading 0: 27%|██▋ | 195/723 [00:29<00:31, 16.63it/s] Loading 0: 27%|██▋ | 198/723 [00:29<00:35, 14.91it/s] Loading 0: 28%|██▊ | 201/723 [00:29<00:33, 15.57it/s] Loading 0: 28%|██▊ | 203/723 [00:29<00:40, 12.99it/s] Loading 0: 29%|██▉ | 210/723 [00:29<00:27, 18.52it/s] Loading 0: 29%|██▉ | 213/723 [00:30<00:31, 16.20it/s] Loading 0: 30%|███ | 218/723 [00:30<00:28, 17.78it/s] Loading 0: 30%|███ | 220/723 [00:30<00:35, 14.32it/s] Loading 0: 31%|███ | 222/723 [00:30<00:35, 14.29it/s] Loading 0: 32%|███▏ | 228/723 [00:31<00:26, 18.34it/s] Loading 0: 32%|███▏ | 230/723 [00:31<00:33, 14.58it/s] Loading 0: 33%|███▎ | 236/723 [00:31<00:26, 18.28it/s] Loading 0: 33%|███▎ | 238/723 [00:31<00:27, 17.41it/s] Loading 0: 33%|███▎ | 242/723 [00:31<00:27, 17.72it/s] Loading 0: 34%|███▎ | 244/723 [00:32<00:28, 16.97it/s] Loading 0: 34%|███▍ | 246/723 [00:32<00:28, 16.61it/s] Loading 0: 34%|███▍ | 248/723 [00:32<00:36, 13.03it/s] Loading 0: 35%|███▌ | 255/723 [00:32<00:24, 19.14it/s] Loading 0: 36%|███▌ | 257/723 [00:32<00:30, 15.05it/s] Loading 0: 36%|███▋ | 263/723 [00:33<00:24, 18.75it/s] Loading 0: 37%|███▋ | 268/723 [00:33<00:23, 19.57it/s] Loading 0: 37%|███▋ | 270/723 [00:48<09:48, 1.30s/it] Loading 0: 38%|███▊ | 273/723 [00:48<07:19, 1.02it/s] Loading 0: 38%|███▊ | 275/723 [00:49<06:05, 1.23it/s] Loading 0: 39%|███▉ | 282/723 [00:49<03:07, 2.35it/s] Loading 0: 39%|███▉ | 284/723 [00:49<02:45, 2.65it/s] Loading 0: 40%|████ | 291/723 [00:49<01:32, 4.69it/s] Loading 0: 41%|████ | 294/723 [00:50<01:17, 5.52it/s] Loading 0: 41%|████ | 297/723 [00:50<01:12, 5.87it/s] Loading 0: 41%|████▏ | 300/723 [00:50<00:58, 7.22it/s] Loading 0: 42%|████▏ | 302/723 [00:50<00:58, 7.25it/s] Loading 0: 43%|████▎ | 309/723 [00:51<00:35, 11.66it/s] Loading 0: 43%|████▎ | 312/723 [00:51<00:35, 11.58it/s] Loading 0: 44%|████▍ | 318/723 [00:51<00:24, 16.65it/s] Loading 0: 44%|████▍ | 321/723 [00:51<00:27, 14.44it/s] Loading 0: 45%|████▍ | 324/723 [00:52<00:29, 13.59it/s] Loading 0: 45%|████▌ | 327/723 [00:52<00:27, 14.26it/s] Loading 0: 46%|████▌ | 329/723 [00:52<00:33, 11.84it/s] Loading 0: 46%|████▌ | 333/723 [00:52<00:25, 15.58it/s] Loading 0: 46%|████▋ | 336/723 [00:52<00:24, 16.01it/s] Loading 0: 47%|████▋ | 338/723 [00:53<00:30, 12.63it/s] Loading 0: 48%|████▊ | 344/723 [00:53<00:22, 16.85it/s] Loading 0: 48%|████▊ | 346/723 [00:53<00:31, 12.11it/s] Loading 0: 48%|████▊ | 348/723 [00:53<00:31, 11.73it/s] Loading 0: 49%|████▊ | 351/723 [00:54<00:26, 14.23it/s] Loading 0: 49%|████▉ | 354/723 [00:54<00:24, 14.78it/s] Loading 0: 49%|████▉ | 356/723 [00:54<00:33, 10.89it/s] Loading 0: 50%|████▉ | 360/723 [00:54<00:24, 14.85it/s] Loading 0: 50%|█████ | 362/723 [00:54<00:26, 13.65it/s] Loading 0: 50%|█████ | 364/723 [00:55<00:28, 12.67it/s] Loading 0: 51%|█████ | 366/723 [00:55<00:25, 13.86it/s] Loading 0: 51%|█████ | 368/723 [00:55<00:25, 14.19it/s] Loading 0: 51%|█████ | 370/723 [00:55<00:27, 13.01it/s] Loading 0: 51%|█████▏ | 372/723 [00:55<00:28, 12.38it/s] Loading 0: 52%|█████▏ | 374/723 [00:56<00:37, 9.20it/s] Loading 0: 53%|█████▎ | 381/723 [00:56<00:22, 15.21it/s] Loading 0: 53%|█████▎ | 383/723 [00:56<00:27, 12.38it/s] Loading 0: 54%|█████▍ | 389/723 [00:56<00:20, 16.19it/s] Loading 0: 54%|█████▍ | 394/723 [00:57<00:18, 17.83it/s] Loading 0: 55%|█████▍ | 396/723 [00:57<00:25, 12.94it/s] Loading 0: 55%|█████▌ | 399/723 [00:57<00:23, 13.65it/s] Loading 0: 55%|█████▌ | 400/723 [01:12<00:23, 13.65it/s] Loading 0: 55%|█████▌ | 401/723 [01:12<08:35, 1.60s/it] Loading 0: 56%|█████▋ | 408/723 [01:13<04:16, 1.23it/s] Loading 0: 57%|█████▋ | 410/723 [01:13<03:38, 1.43it/s] Loading 0: 58%|█████▊ | 417/723 [01:13<01:58, 2.59it/s] Loading 0: 58%|█████▊ | 420/723 [01:13<01:35, 3.16it/s] Loading 0: 59%|█████▊ | 423/723 [01:14<01:22, 3.66it/s] Loading 0: 59%|█████▉ | 426/723 [01:14<01:04, 4.64it/s] Loading 0: 59%|█████▉ | 428/723 [01:14<00:59, 4.99it/s] Loading 0: 60%|██████ | 435/723 [01:14<00:33, 8.50it/s] Loading 0: 61%|██████ | 438/723 [01:15<00:32, 8.84it/s] Loading 0: 61%|██████▏ | 444/723 [01:15<00:21, 12.96it/s] Loading 0: 62%|██████▏ | 447/723 [01:15<00:22, 12.27it/s] Loading 0: 62%|██████▏ | 450/723 [01:15<00:23, 11.71it/s] Loading 0: 63%|██████▎ | 453/723 [01:16<00:22, 11.94it/s] Loading 0: 63%|██████▎ | 455/723 [01:16<00:27, 9.63it/s] Loading 0: 63%|██████▎ | 459/723 [01:16<00:20, 12.93it/s] Loading 0: 64%|██████▍ | 462/723 [01:16<00:19, 13.54it/s] Loading 0: 64%|██████▍ | 464/723 [01:17<00:22, 11.30it/s] Loading 0: 65%|██████▌ | 470/723 [01:17<00:16, 15.49it/s] Loading 0: 65%|██████▌ | 472/723 [01:17<00:22, 11.11it/s] Loading 0: 66%|██████▌ | 474/723 [01:17<00:22, 10.93it/s] Loading 0: 66%|██████▌ | 477/723 [01:18<00:18, 13.14it/s] Loading 0: 66%|██████▋ | 480/723 [01:18<00:17, 13.64it/s] Loading 0: 67%|██████▋ | 482/723 [01:18<00:23, 10.11it/s] Loading 0: 67%|██████▋ | 486/723 [01:18<00:17, 13.87it/s] Loading 0: 67%|██████▋ | 488/723 [01:18<00:18, 12.64it/s] Loading 0: 68%|██████▊ | 490/723 [01:19<00:19, 11.85it/s] Loading 0: 68%|██████▊ | 492/723 [01:19<00:17, 12.84it/s] Loading 0: 68%|██████▊ | 494/723 [01:19<00:18, 12.32it/s] Loading 0: 69%|██████▊ | 496/723 [01:19<00:19, 11.53it/s] Loading 0: 69%|██████▉ | 498/723 [01:19<00:20, 11.09it/s] Loading 0: 69%|██████▉ | 500/723 [01:20<00:26, 8.39it/s] Loading 0: 70%|██████▉ | 504/723 [01:20<00:17, 12.70it/s] Loading 0: 70%|███████ | 507/723 [01:20<00:15, 13.64it/s] Loading 0: 70%|███████ | 509/723 [01:20<00:20, 10.28it/s] Loading 0: 71%|███████ | 513/723 [01:20<00:14, 14.31it/s] Loading 0: 71%|███████ | 515/723 [01:21<00:14, 14.11it/s] Loading 0: 72%|███████▏ | 520/723 [01:21<00:12, 16.49it/s] Loading 0: 72%|███████▏ | 522/723 [01:21<00:18, 11.16it/s] Loading 0: 73%|███████▎ | 525/723 [01:21<00:16, 12.11it/s] Loading 0: 73%|███████▎ | 527/723 [01:22<00:20, 9.75it/s] Loading 0: 73%|███████▎ | 531/723 [01:22<00:13, 13.82it/s] Loading 0: 74%|███████▍ | 534/723 [01:22<00:12, 15.20it/s] Loading 0: 74%|███████▍ | 535/723 [01:32<00:12, 15.20it/s] Loading 0: 74%|███████▍ | 536/723 [01:37<05:13, 1.68s/it] Loading 0: 75%|███████▍ | 542/723 [01:37<02:38, 1.14it/s] Loading 0: 76%|███████▌ | 546/723 [01:37<01:49, 1.62it/s] Loading 0: 76%|███████▌ | 549/723 [01:38<01:26, 2.01it/s] Loading 0: 76%|███████▋ | 552/723 [01:38<01:04, 2.65it/s] Loading 0: 77%|███████▋ | 555/723 [01:38<00:50, 3.34it/s] Loading 0: 78%|███████▊ | 561/723 [01:38<00:29, 5.41it/s] Loading 0: 78%|███████▊ | 564/723 [01:39<00:26, 6.10it/s] Loading 0: 78%|███████▊ | 567/723 [01:39<00:20, 7.61it/s] Loading 0: 79%|███████▉ | 572/723 [01:39<00:14, 10.18it/s] Loading 0: 80%|███████▉ | 575/723 [01:39<00:16, 8.87it/s] Loading 0: 80%|████████ | 579/723 [01:40<00:13, 10.92it/s] Loading 0: 80%|████████ | 581/723 [01:40<00:14, 10.00it/s] Loading 0: 81%|████████ | 586/723 [01:40<00:09, 14.62it/s] Loading 0: 81%|████████▏ | 589/723 [01:40<00:09, 13.44it/s] Loading 0: 82%|████████▏ | 592/723 [01:40<00:08, 14.75it/s] Loading 0: 82%|████████▏ | 595/723 [01:41<00:07, 16.82it/s] Loading 0: 83%|████████▎ | 598/723 [01:41<00:11, 10.63it/s] Loading 0: 83%|████████▎ | 600/723 [01:41<00:11, 10.54it/s] Loading 0: 83%|████████▎ | 603/723 [01:41<00:09, 13.02it/s] Loading 0: 84%|████████▍ | 606/723 [01:42<00:08, 13.87it/s] Loading 0: 84%|████████▍ | 608/723 [01:42<00:10, 11.37it/s] Loading 0: 85%|████████▍ | 614/723 [01:42<00:06, 15.61it/s] Loading 0: 85%|████████▌ | 616/723 [01:42<00:07, 15.10it/s] Loading 0: 86%|████████▌ | 620/723 [01:42<00:06, 16.03it/s] Loading 0: 86%|████████▌ | 622/723 [01:43<00:07, 14.42it/s] Loading 0: 86%|████████▋ | 624/723 [01:43<00:07, 13.41it/s] Loading 0: 87%|████████▋ | 626/723 [01:43<00:09, 9.98it/s] Loading 0: 87%|████████▋ | 631/723 [01:43<00:05, 15.83it/s] Loading 0: 88%|████████▊ | 634/723 [01:44<00:06, 14.62it/s] Loading 0: 88%|████████▊ | 638/723 [01:44<00:04, 18.52it/s] Loading 0: 89%|████████▊ | 641/723 [01:44<00:04, 18.55it/s] Loading 0: 89%|████████▉ | 644/723 [01:44<00:03, 20.70it/s] Loading 0: 89%|████████▉ | 647/723 [01:44<00:05, 14.77it/s] Loading 0: 90%|████████▉ | 649/723 [01:44<00:05, 13.62it/s] Loading 0: 90%|█████████ | 651/723 [01:45<00:05, 13.45it/s] Loading 0: 90%|█████████ | 653/723 [01:45<00:06, 10.70it/s] Loading 0: 91%|█████████ | 658/723 [01:45<00:03, 16.97it/s] Loading 0: 91%|█████████▏| 661/723 [01:45<00:03, 16.08it/s] Loading 0: 92%|█████████▏| 665/723 [01:45<00:02, 20.13it/s] Loading 0: 93%|█████████▎| 672/723 [01:46<00:02, 23.55it/s] Loading 0: 93%|█████████▎| 675/723 [02:01<00:57, 1.19s/it] Loading 0: 94%|█████████▍| 678/723 [02:01<00:41, 1.10it/s] Loading 0: 94%|█████████▍| 681/723 [02:02<00:29, 1.42it/s] Loading 0: 95%|█████████▌| 687/723 [02:02<00:15, 2.39it/s] Loading 0: 95%|█████████▌| 690/723 [02:02<00:11, 3.00it/s] Loading 0: 97%|█████████▋| 698/723 [02:02<00:04, 5.15it/s] Loading 0: 97%|█████████▋| 701/723 [02:03<00:04, 5.48it/s] Loading 0: 98%|█████████▊| 705/723 [02:03<00:02, 6.94it/s] Loading 0: 98%|█████████▊| 708/723 [02:03<00:01, 7.52it/s] Loading 0: 99%|█████████▉| 714/723 [02:03<00:00, 10.47it/s] Loading 0: 99%|█████████▉| 716/723 [02:04<00:00, 9.70it/s] Loading 0: 100%|█████████▉| 722/723 [02:15<00:00, 9.70it/s] Loading 0: 100%|██████████| 723/723 [02:15<00:00, 1.24it/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-v18-mkmlizer: quantized model in 153.753s
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Processed model Undi95/Meta-Llama-3-70B-Instruct-hf in 456.809s
undi95-meta-llama-3-70b-6209-v18-mkmlizer: creating bucket guanaco-mkml-models
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-meta-llama-3-70b-6209-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/config.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/tokenizer.json
Failed to get response for submission sao10k-l3-rp-v4-2_v4: ('http://sao10k-l3-rp-v4-2-v4-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/flywheel_model.5.safetensors
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/flywheel_model.0.safetensors
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/flywheel_model.3.safetensors
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/flywheel_model.4.safetensors
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/flywheel_model.1.safetensors
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v18/flywheel_model.2.safetensors
undi95-meta-llama-3-70b-6209-v18-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
undi95-meta-llama-3-70b-6209-v18-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-v18-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v18-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-v18-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.82s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.14s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.39s/it]
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.08it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.51it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.18it/s]
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Saving duration: 1.384s
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.790s
undi95-meta-llama-3-70b-6209-v18-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-meta-llama-3-70b-6209-v18-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/config.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/merges.txt
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/vocab.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/tokenizer.json
undi95-meta-llama-3-70b-6209-v18-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v18_reward/reward.tensors
Job undi95-meta-llama-3-70b-6209-v18-mkmlizer completed after 528.87s with status: succeeded
Stopping job with name undi95-meta-llama-3-70b-6209-v18-mkmlizer
Pipeline stage MKMLizer completed in 532.37s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service undi95-meta-llama-3-70b-6209-v18
Waiting for inference service undi95-meta-llama-3-70b-6209-v18 to be ready
Failed to get response for submission kaoeiri-pantheramix-l3-r_5669_v1: ('http://kaoeiri-pantheramix-l3-r-5669-v1-predictor-default.tenant-chaiml-guanaco.knative.ord1.coreweave.cloud/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Inference service undi95-meta-llama-3-70b-6209-v18 ready after 164.143461227417s
Pipeline stage ISVCDeployer completed in 166.39s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.149403810501099s
Received healthy response to inference request in 4.053551435470581s
Received healthy response to inference request in 4.1101038455963135s
Received healthy response to inference request in 4.058111667633057s
Received healthy response to inference request in 3.9359679222106934s
5 requests
0 failed requests
5th percentile: 3.9594846248626707
10th percentile: 3.9830013275146485
20th percentile: 4.030034732818604
30th percentile: 4.054463481903076
40th percentile: 4.056287574768066
50th percentile: 4.058111667633057
60th percentile: 4.078908538818359
70th percentile: 4.099705410003662
80th percentile: 4.3179638385772705
90th percentile: 4.733683824539185
95th percentile: 4.941543817520142
99th percentile: 5.107831811904907
mean time: 4.261427736282348
Pipeline stage StressChecker completed in 22.15s
undi95-meta-llama-3-70b_6209_v18 status is now deployed due to DeploymentManager action
undi95-meta-llama-3-70b_6209_v18 status is now deployed due to admin request
undi95-meta-llama-3-70b_6209_v18 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics