submission_id: nousresearch-meta-llama_4941_v88
developer_uid: zonemercy
alignment_samples: 0
best_of: 1
celo_rating: 1115.44
display_name: meta-bo1-base
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '<|user|>', '###'], 'max_input_tokens': 512, 'best_of': 1, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3-8B-Instruct
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: NousResearch/Meta-Llama-
model_name: meta-bo1-base
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
num_battles: 7906
num_wins: 3118
propriety_score: 0.7423312883435583
propriety_total_count: 978.0
ranking_group: single
reward_formatter: {'bot_template': '{bot_name}: {message}\n', 'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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: 2024-07-27T17:23:05+00:00
us_pacific_date: 2024-07-27
win_ratio: 0.39438401214267643
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v88-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v88-mkmlizer to finish
nousresearch-meta-llama-4941-v88-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v88-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
Failed to get response for submission shuttleai-shuttle-2-5-1-mini_v1: ('http://shuttleai-shuttle-2-5-1-mini-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
nousresearch-meta-llama-4941-v88-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ Version: 0.9.7 ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nousresearch-meta-llama-4941-v88-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v88-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-mini_v1: ('http://shuttleai-shuttle-2-5-1-mini-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
nousresearch-meta-llama-4941-v88-mkmlizer: Downloaded to shared memory in 27.351s
nousresearch-meta-llama-4941-v88-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp90smspb6, device:0
nousresearch-meta-llama-4941-v88-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v89-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v89-mkmlizer to finish
nousresearch-meta-llama-4941-v89-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v89-mkmlizer: ║ _____ __ __ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ /___/ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ Version: 0.9.7 ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ https://mk1.ai ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ The license key for the current software has been verified as ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ belonging to: ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ Chai Research Corp. ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
nousresearch-meta-llama-4941-v89-mkmlizer: ║ ║
nousresearch-meta-llama-4941-v89-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v88-mkmlizer: quantized model in 26.354s
nousresearch-meta-llama-4941-v88-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 53.705s
nousresearch-meta-llama-4941-v88-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v88-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v88-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v88
nousresearch-meta-llama-4941-v88-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v88/config.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v88/special_tokens_map.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v88/tokenizer_config.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v88/tokenizer.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v88/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v88-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nousresearch-meta-llama-4941-v88-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 36.35it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 47.36it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:05, 50.29it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 58.68it/s] Loading 0: 13%|█▎ | 38/291 [00:00<00:04, 56.77it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:04, 55.76it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:04, 49.31it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 50.68it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:03, 56.99it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 53.07it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:04, 52.78it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:05, 38.43it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:05, 39.52it/s] Loading 0: 33%|███▎ | 96/291 [00:02<00:04, 40.95it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:03, 47.22it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:03, 46.26it/s] Loading 0: 39%|███▉ | 114/291 [00:02<00:03, 45.12it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 50.97it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 48.38it/s] Loading 0: 46%|████▌ | 133/291 [00:02<00:03, 49.15it/s] Loading 0: 48%|████▊ | 139/291 [00:02<00:02, 51.61it/s] Loading 0: 50%|████▉ | 145/291 [00:02<00:03, 48.26it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 46.96it/s] Loading 0: 54%|█████▍ | 157/291 [00:03<00:02, 51.82it/s] Loading 0: 56%|█████▌ | 163/291 [00:03<00:02, 47.80it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 46.21it/s] Loading 0: 60%|██████ | 176/291 [00:03<00:02, 54.68it/s] Loading 0: 63%|██████▎ | 182/291 [00:03<00:02, 47.41it/s] Loading 0: 65%|██████▍ | 188/291 [00:03<00:02, 37.21it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:02, 38.54it/s] Loading 0: 68%|██████▊ | 199/291 [00:04<00:02, 39.29it/s] Loading 0: 70%|███████ | 204/291 [00:04<00:02, 39.81it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 46.27it/s] Loading 0: 75%|███████▍ | 217/291 [00:04<00:01, 44.96it/s] Loading 0: 76%|███████▋ | 222/291 [00:04<00:01, 44.21it/s] Loading 0: 79%|███████▊ | 229/291 [00:04<00:01, 49.61it/s] Loading 0: 81%|████████ | 235/291 [00:04<00:01, 47.80it/s] Loading 0: 82%|████████▏ | 240/291 [00:05<00:01, 46.28it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 51.67it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 49.11it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 49.84it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 51.46it/s] Loading 0: 93%|█████████▎| 271/291 [00:05<00:00, 47.55it/s] Loading 0: 95%|█████████▍| 276/291 [00:05<00:00, 45.90it/s] Loading 0: 97%|█████████▋| 282/291 [00:05<00:00, 42.78it/s] Loading 0: 99%|█████████▊| 287/291 [00:11<00:01, 3.11it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v88-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v88-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v88-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v88-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.
nousresearch-meta-llama-4941-v88-mkmlizer: warnings.warn(
Failed to get response for submission shuttleai-shuttle-2-5-1-mini_v1: ('http://shuttleai-shuttle-2-5-1-mini-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
nousresearch-meta-llama-4941-v89-mkmlizer: Downloaded to shared memory in 21.042s
nousresearch-meta-llama-4941-v89-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp44_x2qxv, device:0
nousresearch-meta-llama-4941-v89-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v88-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.14s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 3.82s/it] Downloading shards: 100%|██████████| 2/2 [00:08<00:00, 4.01s/it]
nousresearch-meta-llama-4941-v88-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.31it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.81it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.47it/s]
nousresearch-meta-llama-4941-v88-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v88-mkmlizer: Saving duration: 1.348s
nousresearch-meta-llama-4941-v88-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.845s
nousresearch-meta-llama-4941-v88-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v88-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v88-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v88_reward
nousresearch-meta-llama-4941-v88-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v88_reward/config.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v88_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v88_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v88-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v88_reward/merges.txt
nousresearch-meta-llama-4941-v88-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v88_reward/reward.tensors
Job nousresearch-meta-llama-4941-v88-mkmlizer completed after 96.09s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v88-mkmlizer
Pipeline stage MKMLizer completed in 97.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.16s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v88
Waiting for inference service nousresearch-meta-llama-4941-v88 to be ready
nousresearch-meta-llama-4941-v89-mkmlizer: quantized model in 25.662s
nousresearch-meta-llama-4941-v89-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 46.704s
nousresearch-meta-llama-4941-v89-mkmlizer: creating bucket guanaco-mkml-models
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-mini_v1: ('http://shuttleai-shuttle-2-5-1-mini-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'EOF\n')
nousresearch-meta-llama-4941-v89-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v89/tokenizer.json
nousresearch-meta-llama-4941-v89-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v89/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v89-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
nousresearch-meta-llama-4941-v89-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 37.48it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:05, 48.13it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:05, 50.57it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 58.68it/s] Loading 0: 13%|█▎ | 38/291 [00:00<00:04, 56.03it/s] Loading 0: 15%|█▌ | 44/291 [00:00<00:04, 55.09it/s] Loading 0: 17%|█▋ | 50/291 [00:00<00:04, 48.28it/s] Loading 0: 20%|██ | 59/291 [00:01<00:04, 49.78it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:04, 55.92it/s] Loading 0: 25%|██▌ | 73/291 [00:01<00:04, 51.35it/s] Loading 0: 27%|██▋ | 79/291 [00:01<00:04, 51.86it/s] Loading 0: 29%|██▉ | 85/291 [00:01<00:05, 37.23it/s] Loading 0: 31%|███▏ | 91/291 [00:01<00:05, 38.41it/s] Loading 0: 33%|███▎ | 96/291 [00:02<00:04, 40.00it/s] Loading 0: 35%|███▌ | 103/291 [00:02<00:04, 46.21it/s] Loading 0: 37%|███▋ | 109/291 [00:02<00:04, 44.54it/s] Loading 0: 39%|███▉ | 114/291 [00:02<00:04, 43.43it/s] Loading 0: 42%|████▏ | 121/291 [00:02<00:03, 48.48it/s] Loading 0: 44%|████▎ | 127/291 [00:02<00:03, 45.25it/s] Loading 0: 45%|████▌ | 132/291 [00:02<00:03, 45.39it/s] Loading 0: 47%|████▋ | 138/291 [00:02<00:03, 48.96it/s] Loading 0: 49%|████▉ | 144/291 [00:03<00:02, 49.53it/s] Loading 0: 52%|█████▏ | 150/291 [00:03<00:03, 43.74it/s] Loading 0: 54%|█████▎ | 156/291 [00:03<00:02, 46.98it/s] Loading 0: 55%|█████▌ | 161/291 [00:03<00:02, 47.74it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:02, 48.29it/s] Loading 0: 59%|█████▉ | 172/291 [00:03<00:02, 45.88it/s] Loading 0: 62%|██████▏ | 179/291 [00:03<00:02, 49.76it/s] Loading 0: 64%|██████▎ | 185/291 [00:03<00:02, 50.45it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 33.87it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 35.82it/s] Loading 0: 69%|██████▉ | 201/291 [00:04<00:02, 38.41it/s] Loading 0: 71%|███████ | 207/291 [00:04<00:01, 43.11it/s] Loading 0: 73%|███████▎ | 212/291 [00:04<00:02, 38.96it/s] Loading 0: 76%|███████▌ | 220/291 [00:04<00:01, 46.80it/s] Loading 0: 78%|███████▊ | 226/291 [00:04<00:01, 44.83it/s] Loading 0: 79%|███████▉ | 231/291 [00:05<00:01, 45.12it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 50.26it/s] Loading 0: 84%|████████▍ | 244/291 [00:05<00:01, 46.53it/s] Loading 0: 86%|████████▌ | 249/291 [00:05<00:00, 45.93it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 50.37it/s] Loading 0: 90%|█████████ | 262/291 [00:05<00:00, 47.65it/s] Loading 0: 92%|█████████▏| 267/291 [00:05<00:00, 45.91it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 49.97it/s] Loading 0: 96%|█████████▌| 280/291 [00:06<00:00, 47.70it/s] Loading 0: 98%|█████████▊| 285/291 [00:06<00:00, 47.04it/s] Loading 0: 100%|█████████▉| 290/291 [00:11<00:00, 3.30it/s] /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v89-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v89-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v89-mkmlizer: warnings.warn(
nousresearch-meta-llama-4941-v89-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:05<00:05, 5.05s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.72s/it] Downloading shards: 100%|██████████| 2/2 [00:07<00:00, 3.92s/it]
nousresearch-meta-llama-4941-v89-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 2.41it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 4.00it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.64it/s]
nousresearch-meta-llama-4941-v89-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v89-mkmlizer: Saving duration: 1.371s
nousresearch-meta-llama-4941-v89-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 12.638s
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
nousresearch-meta-llama-4941-v89-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v89-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/config.json
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/merges.txt
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/vocab.json
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/tokenizer.json
nousresearch-meta-llama-4941-v89-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v89_reward/reward.tensors
Job nousresearch-meta-llama-4941-v89-mkmlizer completed after 97.37s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v89-mkmlizer
Pipeline stage MKMLizer completed in 98.35s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Creating inference service nousresearch-meta-llama-4941-v89
Waiting for inference service nousresearch-meta-llama-4941-v89 to be ready
Inference service nousresearch-meta-llama-4941-v88 ready after 81.00858187675476s
Pipeline stage ISVCDeployer completed in 82.35s
Running pipeline stage StressChecker
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1_5730_v10: ('http://shuttleai-shuttle-2-5-1-5730-v10-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 2.068951368331909s
Received healthy response to inference request in 1.072786808013916s
Received healthy response to inference request in 1.0638744831085205s
Received healthy response to inference request in 1.0711979866027832s
Failed to get response for submission shuttleai-shuttle-2-5-1-mini_v1: ('http://shuttleai-shuttle-2-5-1-mini-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Received healthy response to inference request in 0.9774293899536133s
5 requests
0 failed requests
5th percentile: 0.9947184085845947
10th percentile: 1.0120074272155761
20th percentile: 1.046585464477539
30th percentile: 1.0653391838073731
Failed to get response for submission shuttleai-shuttle-2-5-1-_5730_v8: ('http://shuttleai-shuttle-2-5-1-5730-v8-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission shuttleai-shuttle-2-5-1-mini_v1: ('http://shuttleai-shuttle-2-5-1-mini-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
40th percentile: 1.0682685852050782
50th percentile: 1.0711979866027832
60th percentile: 1.0718335151672362
70th percentile: 1.0724690437316895
80th percentile: 1.2720197200775147
90th percentile: 1.670485544204712
95th percentile: 1.8697184562683105
99th percentile: 2.0291047859191895
mean time: 1.2508480072021484
Pipeline stage StressChecker completed in 8.13s
nousresearch-meta-llama_4941_v88 status is now deployed due to DeploymentManager action
nousresearch-meta-llama_4941_v88 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v88
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v88 is running
Tearing down inference service nousresearch-meta-llama-4941-v88
Service nousresearch-meta-llama-4941-v88 has been torndown
Pipeline stage ISVCDeleter completed in 4.15s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v88/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v88/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v88/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v88/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v88/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v88_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v88_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v88_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v88_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v88_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v88_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v88_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.03s
nousresearch-meta-llama_4941_v88 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics