submission_id: undi95-meta-llama-3-70b_6209_v19
developer_uid: chai_backend_admin
best_of: 2
celo_rating: 1195.56
display_name: undi95-meta-llama-hollow
family_friendly_score: 0.0
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\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, 'reward_max_tokens': 256}
is_internal_developer: True
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-hollow
model_num_parameters: 70553706496.0
model_repo: Undi95/Meta-Llama-3-70B-Instruct-hf
model_size: 71B
num_battles: 12440
num_wins: 5920
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: 2024-07-23T02:57:46+00:00
us_pacific_date: 2024-07-22
win_ratio: 0.4758842443729904
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Failed to get response for submission mistralai-mixtral-8x7b-_3473_v92: ('http://mistralai-mixtral-8x7b-3473-v92-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Starting job with name undi95-meta-llama-3-70b-6209-v19-mkmlizer
Waiting for job on undi95-meta-llama-3-70b-6209-v19-mkmlizer to finish
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ _____ __ __ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ /___/ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ Version: 0.9.5.post3 ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ https://mk1.ai ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ The license key for the current software has been verified as ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ belonging to: ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ Chai Research Corp. ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ║ ║
undi95-meta-llama-3-70b-6209-v19-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-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 blend_tefuf_2024-07-12: ('http://mistralai-mixtral-8x7b-3473-v86-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\'"}')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission blend_meral_2024-07-13: ('http://neversleep-noromaid-v0-8068-v133-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 blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-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\'"}')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission trace2333-duduk-llama3-v1_v3: ('http://trace2333-duduk-llama3-v1-v3-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 blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-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 blend_meral_2024-07-13: ('http://neversleep-noromaid-v0-8068-v133-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 mistralai-mixtral-8x7b-_3473_v93: ('http://mistralai-mixtral-8x7b-3473-v93-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 blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-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-v19-mkmlizer: Downloaded to shared memory in 394.917s
undi95-meta-llama-3-70b-6209-v19-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpujtjvfqq, device:0
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_meral_2024-07-13: ('http://chaiml-sao10k-l3-rp-v3-3-v37-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 blend_meral_2024-07-13: ('http://neversleep-noromaid-v0-8068-v133-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 mistralai-mixtral-8x7b-_3473_v92: ('http://mistralai-mixtral-8x7b-3473-v92-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:42034->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission blend_meral_2024-07-13: ('http://mistralai-mixtral-8x7b-3473-v86-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-v19-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 0%| | 3/723 [00:00<00:36, 19.89it/s] Loading 0: 1%| | 5/723 [00:00<01:24, 8.54it/s] Loading 0: 1%| | 9/723 [00:00<00:46, 15.29it/s] Loading 0: 2%|▏ | 12/723 [00:00<00:44, 16.04it/s] Loading 0: 2%|▏ | 16/723 [00:01<00:43, 16.29it/s] Loading 0: 2%|▏ | 18/723 [00:01<00:54, 13.00it/s] Loading 0: 3%|▎ | 21/723 [00:01<00:47, 14.94it/s] Loading 0: 3%|▎ | 23/723 [00:01<01:06, 10.46it/s] Loading 0: 4%|▎ | 27/723 [00:01<00:47, 14.60it/s] Loading 0: 4%|▍ | 30/723 [00:02<00:43, 16.03it/s] Loading 0: 5%|▍ | 33/723 [00:02<00:49, 13.85it/s] Loading 0: 5%|▌ | 39/723 [00:02<00:33, 20.51it/s] Loading 0: 6%|▌ | 42/723 [00:02<00:35, 19.40it/s] Loading 0: 6%|▌ | 45/723 [00:03<00:51, 13.21it/s] Loading 0: 7%|▋ | 48/723 [00:03<00:48, 13.87it/s] Loading 0: 7%|▋ | 50/723 [00:03<00:59, 11.28it/s] Loading 0: 7%|▋ | 54/723 [00:03<00:44, 15.12it/s] Loading 0: 8%|▊ | 57/723 [00:03<00:43, 15.33it/s] Loading 0: 8%|▊ | 59/723 [00:04<01:00, 10.97it/s] Loading 0: 9%|▊ | 63/723 [00:04<00:44, 14.78it/s] Loading 0: 9%|▉ | 68/723 [00:04<00:37, 17.43it/s] Loading 0: 10%|▉ | 71/723 [00:05<00:56, 11.48it/s] Loading 0: 10%|█ | 75/723 [00:05<00:54, 11.79it/s] Loading 0: 11%|█ | 77/723 [00:06<01:24, 7.64it/s] Loading 0: 11%|█ | 80/723 [00:06<01:06, 9.71it/s] Loading 0: 12%|█▏ | 84/723 [00:06<01:05, 9.72it/s] Loading 0: 12%|█▏ | 86/723 [00:07<01:31, 6.93it/s] Loading 0: 12%|█▏ | 89/723 [00:07<01:10, 8.97it/s] Loading 0: 13%|█▎ | 91/723 [00:07<01:02, 10.15it/s] Loading 0: 13%|█▎ | 93/723 [00:07<01:23, 7.52it/s] Loading 0: 13%|█▎ | 95/723 [00:08<01:52, 5.58it/s] Loading 0: 14%|█▎ | 98/723 [00:08<01:20, 7.75it/s] Loading 0: 14%|█▍ | 100/723 [00:08<01:07, 9.17it/s] Loading 0: 14%|█▍ | 102/723 [00:09<01:14, 8.30it/s] Loading 0: 14%|█▍ | 104/723 [00:09<01:18, 7.88it/s] Loading 0: 15%|█▌ | 110/723 [00:09<00:41, 14.61it/s] Loading 0: 16%|█▌ | 114/723 [00:09<00:33, 18.32it/s] Loading 0: 16%|█▌ | 117/723 [00:09<00:35, 16.85it/s] Loading 0: 17%|█▋ | 121/723 [00:09<00:30, 19.75it/s] Loading 0: 17%|█▋ | 124/723 [00:19<00:30, 19.75it/s] Loading 0: 17%|█▋ | 125/723 [00:28<15:14, 1.53s/it] Loading 0: 18%|█▊ | 130/723 [00:28<09:40, 1.02it/s] Loading 0: 19%|█▊ | 135/723 [00:28<06:22, 1.54it/s] Loading 0: 19%|█▉ | 140/723 [00:28<04:18, 2.26it/s] Loading 0: 20%|█▉ | 144/723 [00:29<03:19, 2.91it/s] Loading 0: 20%|██ | 148/723 [00:29<02:27, 3.89it/s] Loading 0: 21%|██ | 153/723 [00:29<01:41, 5.61it/s] Loading 0: 22%|██▏ | 157/723 [00:29<01:18, 7.24it/s] Loading 0: 22%|██▏ | 162/723 [00:29<00:55, 10.04it/s] Loading 0: 23%|██▎ | 168/723 [00:29<00:42, 13.03it/s] Loading 0: 24%|██▍ | 172/723 [00:29<00:38, 14.35it/s] Loading 0: 24%|██▍ | 176/723 [00:30<00:34, 15.69it/s] Loading 0: 25%|██▌ | 183/723 [00:30<00:23, 22.56it/s] Loading 0: 26%|██▌ | 187/723 [00:30<00:22, 23.96it/s] Loading 0: 27%|██▋ | 194/723 [00:30<00:20, 25.63it/s] Loading 0: 27%|██▋ | 198/723 [00:30<00:21, 23.97it/s] Loading 0: 28%|██▊ | 202/723 [00:30<00:21, 24.56it/s] Loading 0: 29%|██▊ | 207/723 [00:31<00:17, 28.67it/s] Loading 0: 29%|██▉ | 211/723 [00:31<00:17, 29.08it/s] Loading 0: 30%|██▉ | 216/723 [00:31<00:15, 32.85it/s] Loading 0: 30%|███ | 220/723 [00:31<00:22, 22.36it/s] Loading 0: 31%|███ | 225/723 [00:31<00:18, 26.78it/s] Loading 0: 32%|███▏ | 229/723 [00:31<00:18, 26.70it/s] Loading 0: 32%|███▏ | 233/723 [00:32<00:16, 28.99it/s] Loading 0: 33%|███▎ | 237/723 [00:32<00:18, 26.82it/s] Loading 0: 33%|███▎ | 242/723 [00:32<00:20, 22.93it/s] Loading 0: 34%|███▍ | 246/723 [00:32<00:19, 23.97it/s] Loading 0: 34%|███▍ | 249/723 [00:32<00:20, 23.06it/s] Loading 0: 35%|███▌ | 255/723 [00:32<00:15, 29.74it/s] Loading 0: 36%|███▌ | 259/723 [00:33<00:15, 29.11it/s] Loading 0: 36%|███▋ | 263/723 [00:33<00:15, 30.65it/s] Loading 0: 37%|███▋ | 268/723 [00:33<00:17, 25.42it/s] Loading 0: 37%|███▋ | 271/723 [00:48<08:52, 1.18s/it] Loading 0: 38%|███▊ | 274/723 [00:48<06:46, 1.11it/s] Loading 0: 39%|███▊ | 279/723 [00:49<04:18, 1.72it/s] Loading 0: 39%|███▉ | 283/723 [00:49<03:05, 2.37it/s] Loading 0: 40%|███▉ | 288/723 [00:49<02:03, 3.51it/s] Loading 0: 41%|████ | 294/723 [00:49<01:24, 5.10it/s] Loading 0: 41%|████ | 298/723 [00:49<01:07, 6.30it/s] Loading 0: 42%|████▏ | 301/723 [00:49<00:56, 7.46it/s] Loading 0: 42%|████▏ | 306/723 [00:50<00:40, 10.41it/s] Loading 0: 43%|████▎ | 310/723 [00:50<00:32, 12.67it/s] Loading 0: 44%|████▎ | 315/723 [00:50<00:24, 16.64it/s] Loading 0: 44%|████▍ | 320/723 [00:50<00:22, 17.82it/s] Loading 0: 45%|████▍ | 324/723 [00:50<00:21, 18.27it/s] Loading 0: 45%|████▌ | 328/723 [00:50<00:19, 19.99it/s] Loading 0: 46%|████▌ | 333/723 [00:51<00:16, 24.37it/s] Loading 0: 47%|████▋ | 337/723 [00:51<00:15, 25.62it/s] Loading 0: 47%|████▋ | 342/723 [00:51<00:12, 29.75it/s] Loading 0: 48%|████▊ | 346/723 [00:51<00:17, 21.15it/s] Loading 0: 49%|████▊ | 351/723 [00:51<00:14, 25.54it/s] Loading 0: 49%|████▉ | 355/723 [00:51<00:13, 26.57it/s] Loading 0: 50%|████▉ | 360/723 [00:52<00:11, 30.81it/s] Loading 0: 50%|█████ | 364/723 [00:52<00:11, 30.41it/s] Loading 0: 51%|█████ | 368/723 [00:52<00:13, 25.47it/s] Loading 0: 51%|█████▏ | 372/723 [00:52<00:13, 26.53it/s] Loading 0: 52%|█████▏ | 375/723 [00:52<00:13, 25.45it/s] Loading 0: 53%|█████▎ | 381/723 [00:52<00:10, 32.76it/s] Loading 0: 53%|█████▎ | 385/723 [00:52<00:10, 31.70it/s] Loading 0: 54%|█████▍ | 389/723 [00:52<00:09, 33.46it/s] Loading 0: 54%|█████▍ | 394/723 [00:53<00:11, 29.21it/s] Loading 0: 55%|█████▌ | 398/723 [00:53<00:11, 28.22it/s] Loading 0: 56%|█████▌ | 402/723 [01:07<05:39, 1.06s/it] Loading 0: 56%|█████▋ | 408/723 [01:07<03:29, 1.51it/s] Loading 0: 57%|█████▋ | 412/723 [01:08<02:34, 2.01it/s] Loading 0: 58%|█████▊ | 420/723 [01:08<01:30, 3.35it/s] Loading 0: 59%|█████▊ | 424/723 [01:08<01:11, 4.16it/s] Loading 0: 59%|█████▉ | 427/723 [01:08<00:59, 4.98it/s] Loading 0: 60%|█████▉ | 432/723 [01:08<00:41, 7.00it/s] Loading 0: 60%|██████ | 436/723 [01:08<00:32, 8.82it/s] Loading 0: 61%|██████ | 441/723 [01:09<00:23, 11.95it/s] Loading 0: 62%|██████▏ | 446/723 [01:09<00:19, 14.08it/s] Loading 0: 62%|██████▏ | 450/723 [01:09<00:17, 15.26it/s] Loading 0: 63%|██████▎ | 454/723 [01:09<00:15, 17.32it/s] Loading 0: 63%|██████▎ | 459/723 [01:09<00:12, 21.76it/s] Loading 0: 64%|██████▍ | 463/723 [01:09<00:11, 23.57it/s] Loading 0: 65%|██████▍ | 468/723 [01:10<00:09, 27.97it/s] Loading 0: 65%|██████▌ | 472/723 [01:10<00:11, 20.94it/s] Loading 0: 66%|██████▌ | 477/723 [01:10<00:09, 25.53it/s] Loading 0: 67%|██████▋ | 481/723 [01:10<00:09, 26.80it/s] Loading 0: 67%|██████▋ | 486/723 [01:10<00:07, 31.33it/s] Loading 0: 68%|██████▊ | 490/723 [01:10<00:07, 30.99it/s] Loading 0: 68%|██████▊ | 494/723 [01:11<00:08, 26.70it/s] Loading 0: 69%|██████▉ | 498/723 [01:11<00:08, 27.83it/s] Loading 0: 69%|██████▉ | 502/723 [01:11<00:07, 28.25it/s] Loading 0: 70%|███████ | 507/723 [01:11<00:06, 32.89it/s] Loading 0: 71%|███████ | 511/723 [01:11<00:06, 31.87it/s] Loading 0: 71%|███████ | 515/723 [01:11<00:06, 33.51it/s] Loading 0: 72%|███████▏ | 520/723 [01:11<00:06, 29.26it/s] Loading 0: 72%|███████▏ | 524/723 [01:11<00:06, 29.33it/s] Loading 0: 73%|███████▎ | 528/723 [01:12<00:07, 26.10it/s] Loading 0: 74%|███████▍ | 534/723 [01:12<00:05, 32.78it/s] Loading 0: 74%|███████▍ | 538/723 [01:26<02:57, 1.04it/s] Loading 0: 76%|███████▌ | 546/723 [01:26<01:39, 1.78it/s] Loading 0: 76%|███████▌ | 550/723 [01:26<01:16, 2.27it/s] Loading 0: 76%|███████▋ | 553/723 [01:27<01:01, 2.77it/s] Loading 0: 77%|███████▋ | 558/723 [01:27<00:41, 3.99it/s] Loading 0: 78%|███████▊ | 562/723 [01:27<00:30, 5.21it/s] Loading 0: 78%|███████▊ | 567/723 [01:27<00:21, 7.32it/s] Loading 0: 79%|███████▉ | 572/723 [01:27<00:16, 9.42it/s] Loading 0: 80%|███████▉ | 576/723 [01:27<00:13, 11.00it/s] Loading 0: 80%|████████ | 580/723 [01:27<00:10, 13.16it/s] Loading 0: 81%|████████ | 585/723 [01:28<00:08, 17.23it/s] Loading 0: 81%|████████▏ | 589/723 [01:28<00:06, 19.56it/s] Loading 0: 82%|████████▏ | 594/723 [01:28<00:05, 24.12it/s] Loading 0: 83%|████████▎ | 598/723 [01:28<00:06, 19.38it/s] Loading 0: 83%|████████▎ | 603/723 [01:28<00:05, 24.00it/s] Loading 0: 84%|████████▍ | 607/723 [01:28<00:04, 25.37it/s] Loading 0: 85%|████████▍ | 612/723 [01:28<00:03, 29.69it/s] Loading 0: 85%|████████▌ | 616/723 [01:29<00:03, 29.44it/s] Loading 0: 86%|████████▌ | 620/723 [01:29<00:04, 25.19it/s] Loading 0: 86%|████████▋ | 624/723 [01:29<00:03, 26.61it/s] Loading 0: 87%|████████▋ | 628/723 [01:29<00:03, 27.33it/s] Loading 0: 88%|████████▊ | 633/723 [01:29<00:02, 32.00it/s] Loading 0: 88%|████████▊ | 637/723 [01:29<00:02, 30.04it/s] Loading 0: 89%|████████▊ | 641/723 [01:29<00:02, 31.16it/s] Loading 0: 89%|████████▉ | 646/723 [01:30<00:02, 26.19it/s] Loading 0: 90%|████████▉ | 649/723 [01:30<00:03, 24.45it/s] Loading 0: 90%|█████████ | 652/723 [01:30<00:02, 23.71it/s] Loading 0: 91%|█████████ | 657/723 [01:30<00:02, 28.31it/s] Loading 0: 91%|█████████▏| 661/723 [01:30<00:02, 28.32it/s] Loading 0: 92%|█████████▏| 666/723 [01:30<00:01, 32.03it/s] Loading 0: 93%|█████████▎| 672/723 [01:31<00:01, 28.35it/s] Loading 0: 93%|█████████▎| 676/723 [01:45<00:45, 1.04it/s] Loading 0: 94%|█████████▍| 679/723 [01:45<00:33, 1.32it/s] Loading 0: 95%|█████████▍| 684/723 [01:45<00:19, 1.97it/s] Loading 0: 95%|█████████▌| 688/723 [01:45<00:13, 2.67it/s] Loading 0: 96%|█████████▌| 693/723 [01:45<00:07, 3.89it/s] Loading 0: 97%|█████████▋| 698/723 [01:46<00:04, 5.27it/s] Loading 0: 97%|█████████▋| 702/723 [01:46<00:03, 6.56it/s] Loading 0: 98%|█████████▊| 706/723 [01:46<00:02, 8.30it/s] Loading 0: 98%|█████████▊| 711/723 [01:46<00:01, 11.38it/s] Loading 0: 99%|█████████▉| 715/723 [01:46<00:00, 13.76it/s] Loading 0: 100%|█████████▉| 720/723 [01:46<00:00, 17.89it/s] Loading 0: 100%|█████████▉| 722/723 [01:57<00:00, 17.89it/s] Loading 0: 100%|██████████| 723/723 [01:57<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-v19-mkmlizer: quantized model in 135.749s
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Processed model Undi95/Meta-Llama-3-70B-Instruct-hf in 530.666s
undi95-meta-llama-3-70b-6209-v19-mkmlizer: creating bucket guanaco-mkml-models
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
undi95-meta-llama-3-70b-6209-v19-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/config.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/tokenizer.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/flywheel_model.5.safetensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/flywheel_model.3.safetensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/flywheel_model.1.safetensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/flywheel_model.4.safetensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/flywheel_model.0.safetensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/undi95-meta-llama-3-70b-6209-v19/flywheel_model.2.safetensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
undi95-meta-llama-3-70b-6209-v19-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-v19-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v19-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-v19-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v19-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-v19-mkmlizer: warnings.warn(
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.22s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.87s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.07s/it]
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.30it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.71it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.40it/s]
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
undi95-meta-llama-3-70b-6209-v19-mkmlizer: creating bucket guanaco-reward-models
undi95-meta-llama-3-70b-6209-v19-mkmlizer: Bucket 's3://guanaco-reward-models/' created
undi95-meta-llama-3-70b-6209-v19-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/config.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/tokenizer_config.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/special_tokens_map.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/merges.txt
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/vocab.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/tokenizer.json
undi95-meta-llama-3-70b-6209-v19-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/undi95-meta-llama-3-70b-6209-v19_reward/reward.tensors
Job undi95-meta-llama-3-70b-6209-v19-mkmlizer completed after 597.14s with status: succeeded
Stopping job with name undi95-meta-llama-3-70b-6209-v19-mkmlizer
Pipeline stage MKMLizer completed in 598.13s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service undi95-meta-llama-3-70b-6209-v19
Waiting for inference service undi95-meta-llama-3-70b-6209-v19 to be ready
Failed to get response for submission blend_meral_2024-07-13: ('http://neversleep-noromaid-v0-8068-v133-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 mistralai-mixtral-8x7b-_3473_v93: ('http://mistralai-mixtral-8x7b-3473-v93-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 blend_meral_2024-07-13: ('http://chaiml-sao10k-l3-rp-v3-3-v37-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-elo-alignment-run-3_v12: ('http://chaiml-elo-alignment-run-3-v12-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-v19 ready after 131.57632565498352s
Pipeline stage ISVCDeployer completed in 133.28s
Running pipeline stage StressChecker
Received healthy response to inference request in 5.128987073898315s
Received healthy response to inference request in 3.552110195159912s
Received healthy response to inference request in 3.358855724334717s
Received healthy response to inference request in 3.678358554840088s
Received healthy response to inference request in 3.3860363960266113s
5 requests
0 failed requests
5th percentile: 3.364291858673096
10th percentile: 3.3697279930114745
20th percentile: 3.3806002616882322
30th percentile: 3.4192511558532717
40th percentile: 3.485680675506592
50th percentile: 3.552110195159912
60th percentile: 3.6026095390319823
70th percentile: 3.6531088829040526
80th percentile: 3.9684842586517335
90th percentile: 4.548735666275024
95th percentile: 4.838861370086669
99th percentile: 5.070961933135986
mean time: 3.8208695888519286
Pipeline stage StressChecker completed in 20.00s
undi95-meta-llama-3-70b_6209_v19 status is now deployed due to DeploymentManager action
undi95-meta-llama-3-70b_6209_v19 status is now inactive due to auto deactivation removed underperforming models
undi95-meta-llama-3-70b_6209_v19 status is now deployed due to admin request
undi95-meta-llama-3-70b_6209_v19 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of undi95-meta-llama-3-70b_6209_v19
Running pipeline stage ISVCDeleter
Checking if service undi95-meta-llama-3-70b-6209-v19 is running
Tearing down inference service undi95-meta-llama-3-70b-6209-v19
Service undi95-meta-llama-3-70b-6209-v19 has been torndown
Pipeline stage ISVCDeleter completed in 4.37s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key undi95-meta-llama-3-70b-6209-v19/config.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/flywheel_model.2.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/flywheel_model.3.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/flywheel_model.4.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/flywheel_model.5.safetensors from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/tokenizer.json from bucket guanaco-mkml-models
Deleting key undi95-meta-llama-3-70b-6209-v19/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/config.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/merges.txt from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/reward.tensors from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key undi95-meta-llama-3-70b-6209-v19_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 12.31s
undi95-meta-llama-3-70b_6209_v19 status is now torndown due to DeploymentManager action