submission_id: jellywibble-lora-120k-pr_2801_v5
developer_uid: zonemercy
status: inactive
model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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}
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}
reward_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}
timestamp: 2024-07-12T02:33:15+00:00
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: Jellywibble/lora_120k_pr
num_battles: 20524
num_wins: 12016
celo_rating: 1261.03
propriety_score: 0.7168874172185431
propriety_total_count: 5436.0
submission_type: basic
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 16
max_input_tokens: 512
max_output_tokens: 64
display_name: nitral-ai-hathor-l3-8b-v-01_v1
ineligible_reason: None
language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment
model_size: 8B
reward_model: ChaiML/gpt2_xl_pairwise_89m_step_347634
us_pacific_date: 2024-07-11
win_ratio: 0.5854609237965309
preference_data_url: None
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-2801-v5-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2801-v5-mkmlizer to finish
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ _____ __ __ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ /___/ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ https://mk1.ai ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ belonging to: ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ Chai Research Corp. ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-2801-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Downloaded to shared memory in 62.225s
jellywibble-lora-120k-pr-2801-v5-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:06, 44.04it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:04, 63.82it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:03, 70.81it/s] Loading 0: 10%|▉ | 29/291 [00:00<00:03, 73.65it/s] Loading 0: 13%|█▎ | 37/291 [00:00<00:08, 31.01it/s] Loading 0: 15%|█▍ | 43/291 [00:01<00:07, 34.97it/s] Loading 0: 17%|█▋ | 50/291 [00:01<00:06, 39.19it/s] Loading 0: 20%|██ | 59/291 [00:01<00:05, 46.29it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:04, 51.77it/s] Loading 0: 26%|██▌ | 75/291 [00:01<00:03, 55.57it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:06, 31.34it/s] Loading 0: 31%|███▏ | 91/291 [00:02<00:05, 38.33it/s] Loading 0: 34%|███▍ | 99/291 [00:02<00:04, 45.36it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:03, 49.84it/s] Loading 0: 39%|███▉ | 113/291 [00:02<00:03, 50.93it/s] Loading 0: 42%|████▏ | 122/291 [00:02<00:02, 58.28it/s] Loading 0: 44%|████▍ | 129/291 [00:02<00:02, 59.03it/s] Loading 0: 47%|████▋ | 136/291 [00:03<00:04, 32.33it/s] Loading 0: 48%|████▊ | 141/291 [00:03<00:04, 34.16it/s] Loading 0: 51%|█████ | 148/291 [00:03<00:03, 39.93it/s] Loading 0: 54%|█████▎ | 156/291 [00:03<00:02, 47.16it/s] Loading 0: 56%|█████▌ | 162/291 [00:03<00:02, 49.27it/s] Loading 0: 58%|█████▊ | 168/291 [00:03<00:02, 49.31it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:02, 53.18it/s] Loading 0: 64%|██████▍ | 186/291 [00:04<00:03, 32.69it/s] Loading 0: 66%|██████▌ | 191/291 [00:04<00:02, 34.30it/s] Loading 0: 67%|██████▋ | 196/291 [00:04<00:02, 35.95it/s] Loading 0: 70%|██████▉ | 203/291 [00:04<00:02, 39.69it/s] Loading 0: 73%|███████▎ | 211/291 [00:04<00:01, 47.39it/s] Loading 0: 75%|███████▌ | 219/291 [00:04<00:01, 54.35it/s] Loading 0: 78%|███████▊ | 226/291 [00:05<00:01, 57.69it/s] Loading 0: 80%|████████ | 233/291 [00:05<00:01, 30.77it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 33.07it/s] Loading 0: 85%|████████▍ | 246/291 [00:05<00:01, 40.39it/s] Loading 0: 87%|████████▋ | 253/291 [00:05<00:00, 46.12it/s] Loading 0: 89%|████████▉ | 259/291 [00:05<00:00, 47.14it/s] Loading 0: 91%|█████████▏| 266/291 [00:06<00:00, 48.44it/s] Loading 0: 94%|█████████▍| 274/291 [00:06<00:00, 55.41it/s] Loading 0: 97%|█████████▋| 281/291 [00:06<00:00, 58.80it/s] Loading 0: 99%|█████████▉| 288/291 [00:13<00:00, 3.18it/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-v5-mkmlizer: quantized model in 32.668s
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 94.893s
jellywibble-lora-120k-pr-2801-v5-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-2801-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v5
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v5/tokenizer.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v5/config.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v5/tokenizer_config.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v5/special_tokens_map.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v5/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-2801-v5-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-2801-v5-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-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-2801-v5-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-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-2801-v5-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-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-2801-v5-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-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.47it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.48it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.25it/s]
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Saving duration: 2.274s
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 21.007s
jellywibble-lora-120k-pr-2801-v5-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-2801-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-2801-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/config.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/tokenizer_config.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/vocab.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/merges.txt
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/special_tokens_map.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/tokenizer.json
jellywibble-lora-120k-pr-2801-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v5_reward/reward.tensors
Job jellywibble-lora-120k-pr-2801-v5-mkmlizer completed after 147.21s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-2801-v5-mkmlizer
Pipeline stage MKMLizer completed in 148.04s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-2801-v5
Waiting for inference service jellywibble-lora-120k-pr-2801-v5 to be ready
Inference service jellywibble-lora-120k-pr-2801-v5 ready after 50.243165254592896s
Pipeline stage ISVCDeployer completed in 57.18s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3417651653289795s
Received healthy response to inference request in 1.5777263641357422s
Received healthy response to inference request in 1.5453872680664062s
Received healthy response to inference request in 1.5163354873657227s
Received healthy response to inference request in 1.5756385326385498s
5 requests
0 failed requests
5th percentile: 1.5221458435058595
10th percentile: 1.527956199645996
20th percentile: 1.5395769119262694
30th percentile: 1.5514375209808349
40th percentile: 1.5635380268096923
50th percentile: 1.5756385326385498
60th percentile: 1.5764736652374267
70th percentile: 1.5773087978363036
80th percentile: 1.7305341243743897
90th percentile: 2.0361496448516845
95th percentile: 2.1889574050903318
99th percentile: 2.31120361328125
mean time: 1.7113705635070802
Pipeline stage StressChecker completed in 9.31s
jellywibble-lora-120k-pr_2801_v5 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_2801_v5 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics