jellywibble-lora-120k-pr_2801

submission_id: jellywibble-lora-120k-pr_2801_v1
developer_uid: Jellywibble
best_of: 16
celo_rating: 1265.74
display_name: nitral-ai-hathor-l3-8b-v-01_v1
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{bot_name}'s Persona: {memory}\n\n", 'prompt_template': '{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}: {message}<|eot_id|>', 'user_template': '<|start_header_id|>user<|end_header_id|>\n\n{user_name}: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.08, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: True
language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Jellywibble/lora_120k_pr
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_num_parameters: 8030261248.0
model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
model_size: 8B
num_battles: 32742
num_wins: 19717
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: 2024-07-08T03:31:54+00:00
us_pacific_date: 2024-07-07
win_ratio: 0.6021929020829515
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-2801-v1-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2801-v1-mkmlizer to finish
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-p-2827-v10-mkmlizer
Waiting for job on jellywibble-lora-120k-p-2827-v10-mkmlizer to finish
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Downloaded to shared memory in 63.844s
jellywibble-lora-120k-pr-2801-v1-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-p-2827-v10-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2827-v10-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-2801-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 37.28it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 59.17it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 67.32it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:03, 68.15it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:08, 29.92it/s]
Loading 0:  14%|█▎        | 40/291 [00:01<00:07, 32.94it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:05, 42.14it/s]
Loading 0:  19%|█▉        | 55/291 [00:01<00:04, 48.15it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:04, 50.30it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 49.65it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:03, 54.66it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:06, 30.69it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:05, 38.27it/s]
Loading 0:  33%|███▎      | 97/291 [00:02<00:04, 44.06it/s]
Loading 0:  35%|███▌      | 103/291 [00:02<00:04, 44.44it/s]
Loading 0:  37%|███▋      | 109/291 [00:02<00:03, 47.67it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:03, 52.36it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:02, 61.65it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 33.35it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:04, 35.17it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 42.37it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 48.36it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 53.06it/s]
Loading 0:  60%|█████▉    | 174/291 [00:03<00:02, 58.00it/s]
Loading 0:  62%|██████▏   | 181/291 [00:03<00:01, 60.07it/s]
Loading 0:  65%|██████▍   | 188/291 [00:04<00:03, 33.35it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:02, 34.35it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 42.17it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:01, 48.85it/s]
Loading 0:  75%|███████▍  | 217/291 [00:04<00:01, 52.38it/s]
Loading 0:  77%|███████▋  | 224/291 [00:04<00:01, 50.81it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 50.45it/s]
Loading 0:  81%|████████  | 236/291 [00:05<00:01, 30.13it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 32.56it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 37.10it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 45.14it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 52.21it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 56.00it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 55.89it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  3.33it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-pr-2801-v1-mkmlizer: quantized model in 32.384s
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 96.229s
jellywibble-lora-120k-pr-2801-v1-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-2801-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v1
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v1/config.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v1/tokenizer_config.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v1/special_tokens_map.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v1/tokenizer.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-2801-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-2801-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
jellywibble-lora-120k-pr-2801-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-2801-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-pr-2801-v1-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2827-v10-mkmlizer: Downloaded to shared memory in 44.268s
jellywibble-lora-120k-p-2827-v10-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-p-2827-v10-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-2801-v1-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:16<00:16, 16.21s/it]
Downloading shards: 100%|██████████| 2/2 [00:19<00:00,  8.55s/it]
Downloading shards: 100%|██████████| 2/2 [00:19<00:00,  9.70s/it]
jellywibble-lora-120k-pr-2801-v1-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.48it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.45it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.23it/s]
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Saving duration: 2.294s
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 24.661s
jellywibble-lora-120k-pr-2801-v1-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-2801-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-2801-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/config.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/tokenizer_config.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/vocab.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/special_tokens_map.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/tokenizer.json
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/merges.txt
jellywibble-lora-120k-pr-2801-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v1_reward/reward.tensors
Job jellywibble-lora-120k-pr-2801-v1-mkmlizer completed after 167.19s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-2801-v1-mkmlizer
Pipeline stage MKMLizer completed in 168.17s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-2801-v1
jellywibble-lora-120k-p-2827-v10-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 44.47it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 58.81it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 62.45it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:07, 35.35it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:06, 37.56it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:06, 39.45it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 43.39it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 50.14it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 55.26it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 60.86it/s]
Loading 0:  29%|██▊       | 83/291 [00:02<00:06, 32.32it/s]
Loading 0:  32%|███▏      | 92/291 [00:02<00:05, 39.18it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 46.12it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 51.09it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 54.83it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:02, 60.60it/s]
Loading 0:  45%|████▌     | 132/291 [00:02<00:02, 62.58it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:04, 31.58it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 38.79it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 45.14it/s]
Loading 0:  56%|█████▌    | 163/291 [00:03<00:02, 49.82it/s]
Loading 0:  58%|█████▊    | 170/291 [00:03<00:02, 51.18it/s]
Loading 0:  61%|██████    | 177/291 [00:03<00:02, 52.12it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 35.42it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 36.66it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 37.33it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 41.18it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:01, 48.41it/s]
Loading 0:  74%|███████▍  | 216/291 [00:04<00:01, 50.23it/s]
Loading 0:  76%|███████▋  | 222/291 [00:04<00:01, 49.86it/s]
Loading 0:  78%|███████▊  | 228/291 [00:05<00:01, 51.20it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:02, 28.38it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 31.59it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:01, 40.14it/s]
Loading 0:  88%|████████▊ | 257/291 [00:05<00:00, 47.25it/s]
Loading 0:  91%|█████████▏| 266/291 [00:05<00:00, 52.96it/s]
Loading 0:  94%|█████████▍| 274/291 [00:06<00:00, 57.94it/s]
Loading 0:  97%|█████████▋| 281/291 [00:06<00:00, 59.69it/s]
Loading 0:  99%|█████████▉| 288/291 [00:13<00:00,  3.41it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-p-2827-v10-mkmlizer: quantized model in 31.732s
jellywibble-lora-120k-p-2827-v10-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep2 in 76.000s
jellywibble-lora-120k-p-2827-v10-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-p-2827-v10-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-p-2827-v10-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-p-2827-v10
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2827-v10/config.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2827-v10/tokenizer_config.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2827-v10/special_tokens_map.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2827-v10/tokenizer.json
Waiting for inference service jellywibble-lora-120k-pr-2801-v1 to be ready
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-p-2827-v10/flywheel_model.0.safetensors
jellywibble-lora-120k-p-2827-v10-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-p-2827-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:919: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-p-2827-v10-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2827-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
jellywibble-lora-120k-p-2827-v10-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2827-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:769: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-p-2827-v10-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2827-v10-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-p-2827-v10-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2827-v10-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.21s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  3.71s/it]
Downloading shards: 100%|██████████| 2/2 [00:08<00:00,  4.09s/it]
jellywibble-lora-120k-p-2827-v10-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.66it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.71it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.47it/s]
jellywibble-lora-120k-p-2827-v10-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-p-2827-v10-mkmlizer: Saving duration: 2.145s
jellywibble-lora-120k-p-2827-v10-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 13.275s
jellywibble-lora-120k-p-2827-v10-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-p-2827-v10-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-p-2827-v10-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward/config.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward/tokenizer_config.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward/special_tokens_map.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward/vocab.json
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward/merges.txt
jellywibble-lora-120k-p-2827-v10-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2827-v10_reward/tokenizer.json
Job jellywibble-lora-120k-p-2827-v10-mkmlizer completed after 126.87s with status: succeeded
Stopping job with name jellywibble-lora-120k-p-2827-v10-mkmlizer
Pipeline stage MKMLizer completed in 127.42s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.17s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-p-2827-v10
Waiting for inference service jellywibble-lora-120k-p-2827-v10 to be ready
Inference service jellywibble-lora-120k-pr-2801-v1 ready after 130.58460521697998s
Pipeline stage ISVCDeployer completed in 137.85s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.202462911605835s
Received healthy response to inference request in 1.5806307792663574s
Received healthy response to inference request in 1.5437219142913818s
Received healthy response to inference request in 1.5461797714233398s
Received healthy response to inference request in 1.5864455699920654s
5 requests
0 failed requests
5th percentile: 1.5442134857177734
10th percentile: 1.544705057144165
20th percentile: 1.5456881999969483
30th percentile: 1.5530699729919433
40th percentile: 1.5668503761291503
50th percentile: 1.5806307792663574
60th percentile: 1.5829566955566405
70th percentile: 1.5852826118469239
80th percentile: 1.7096490383148195
90th percentile: 1.9560559749603272
95th percentile: 2.079259443283081
99th percentile: 2.177822217941284
mean time: 1.691888189315796
Pipeline stage StressChecker completed in 10.41s
jellywibble-lora-120k-pr_2801_v1 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_2801_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_2801_v1
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-2801-v1 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.43s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2801-v1/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.89s
jellywibble-lora-120k-pr_2801_v1 status is now torndown due to DeploymentManager action