developer_uid: zonemercy
submission_id: jellywibble-lora-120k-pr_7199_v5
model_name: nitral-ai-hathor-l3-8b-v-01_v1
model_group: Jellywibble/lora_120k_pr
status: torndown
timestamp: 2024-07-12T20:41:15+00:00
num_battles: 24414
num_wins: 14748
celo_rating: 1267.16
family_friendly_score: 0.0
submission_type: basic
model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_only
model_architecture: LlamaForCausalLM
reward_repo: ChaiML/gpt2_xl_pairwise_89m_step_347634
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
is_internal_developer: True
language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_only
model_size: 8B
ranking_group: single
us_pacific_date: 2024-07-12
win_ratio: 0.6040796264438437
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: {'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'}
Resubmit model
Running pipeline stage MKMLizer
Starting job with name jellywibble-lora-120k-pr-7199-v5-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-7199-v5-mkmlizer to finish
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ _____ __ __ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ /___/ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ Version: 0.8.14 ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ https://mk1.ai ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ The license key for the current software has been verified as ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ belonging to: ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ Chai Research Corp. ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ║ ║
jellywibble-lora-120k-pr-7199-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Downloaded to shared memory in 67.848s
jellywibble-lora-120k-pr-7199-v5-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:07, 40.41it/s] Loading 0: 5%|▍ | 14/291 [00:00<00:04, 66.78it/s] Loading 0: 8%|▊ | 23/291 [00:00<00:03, 76.36it/s] Loading 0: 11%|█▏ | 33/291 [00:00<00:05, 49.19it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:05, 49.80it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 59.06it/s] Loading 0: 20%|██ | 59/291 [00:00<00:03, 65.14it/s] Loading 0: 23%|██▎ | 68/291 [00:01<00:03, 71.38it/s] Loading 0: 27%|██▋ | 80/291 [00:01<00:03, 52.81it/s] Loading 0: 30%|██▉ | 87/291 [00:01<00:03, 55.98it/s] Loading 0: 33%|███▎ | 96/291 [00:01<00:03, 63.12it/s] Loading 0: 36%|███▌ | 105/291 [00:01<00:02, 68.87it/s] Loading 0: 39%|███▉ | 114/291 [00:01<00:02, 73.47it/s] Loading 0: 43%|████▎ | 125/291 [00:01<00:02, 81.91it/s] Loading 0: 46%|████▌ | 134/291 [00:02<00:03, 50.26it/s] Loading 0: 48%|████▊ | 141/291 [00:02<00:02, 52.63it/s] Loading 0: 51%|█████ | 149/291 [00:02<00:02, 57.91it/s] Loading 0: 54%|█████▍ | 158/291 [00:02<00:02, 64.37it/s] Loading 0: 57%|█████▋ | 167/291 [00:02<00:01, 70.47it/s] Loading 0: 60%|██████ | 176/291 [00:02<00:01, 75.21it/s] Loading 0: 64%|██████▍ | 186/291 [00:03<00:01, 54.80it/s] Loading 0: 66%|██████▋ | 193/291 [00:03<00:01, 52.59it/s] Loading 0: 69%|██████▉ | 202/291 [00:03<00:01, 59.41it/s] Loading 0: 73%|███████▎ | 211/291 [00:03<00:01, 64.93it/s] Loading 0: 76%|███████▌ | 220/291 [00:03<00:01, 69.62it/s] Loading 0: 78%|███████▊ | 228/291 [00:03<00:00, 70.13it/s] Loading 0: 81%|████████ | 236/291 [00:03<00:01, 46.77it/s] Loading 0: 83%|████████▎ | 242/291 [00:04<00:01, 48.58it/s] Loading 0: 85%|████████▌ | 248/291 [00:04<00:00, 50.90it/s] Loading 0: 88%|████████▊ | 257/291 [00:04<00:00, 58.62it/s] Loading 0: 91%|█████████▏| 266/291 [00:04<00:00, 63.61it/s] Loading 0: 95%|█████████▍| 275/291 [00:04<00:00, 65.48it/s] Loading 0: 98%|█████████▊| 286/291 [00:10<00:01, 4.70it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-pr-7199-v5-mkmlizer: quantized model in 29.555s
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_only in 97.403s
jellywibble-lora-120k-pr-7199-v5-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-7199-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v5
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v5/config.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v5/tokenizer_config.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v5/special_tokens_map.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v5/tokenizer.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-7199-v5/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-7199-v5-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-7199-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-7199-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-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-7199-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-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-7199-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-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-7199-v5-mkmlizer: warnings.warn(
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Downloading shards: 0%| | 0/2 [00:00<?, ?it/s] Downloading shards: 50%|█████ | 1/2 [00:06<00:06, 6.46s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.81s/it] Downloading shards: 100%|██████████| 2/2 [00:11<00:00, 5.91s/it]
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s] Loading checkpoint shards: 50%|█████ | 1/2 [00:00<00:00, 1.82it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 3.05it/s] Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00, 2.77it/s]
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Saving duration: 3.088s
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 17.304s
jellywibble-lora-120k-pr-7199-v5-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-7199-v5-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-7199-v5-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/tokenizer_config.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/special_tokens_map.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/config.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/vocab.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/merges.txt
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/tokenizer.json
jellywibble-lora-120k-pr-7199-v5-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-pr-7199-v5_reward/reward.tensors
Connection pool is full, discarding connection: %s
Job jellywibble-lora-120k-pr-7199-v5-mkmlizer completed after 753.59s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-7199-v5-mkmlizer
Pipeline stage MKMLizer completed in 754.49s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-7199-v5
Waiting for inference service jellywibble-lora-120k-pr-7199-v5 to be ready
Inference service jellywibble-lora-120k-pr-7199-v5 ready after 50.31143641471863s
Pipeline stage ISVCDeployer completed in 57.44s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.731732130050659s
Received healthy response to inference request in 3.1140336990356445s
Received healthy response to inference request in 1.5627214908599854s
Received healthy response to inference request in 1.5282387733459473s
Received healthy response to inference request in 3.574676990509033s
5 requests
0 failed requests
5th percentile: 1.535135316848755
10th percentile: 1.5420318603515626
20th percentile: 1.5558249473571777
30th percentile: 1.8729839324951172
40th percentile: 2.493508815765381
50th percentile: 3.1140336990356445
60th percentile: 3.298291015625
70th percentile: 3.4825483322143556
80th percentile: 3.8060880184173587
90th percentile: 4.268910074234009
95th percentile: 4.500321102142334
99th percentile: 4.685449924468994
mean time: 2.9022806167602537
Pipeline stage StressChecker completed in 15.28s
jellywibble-lora-120k-pr_7199_v5 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_7199_v5 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_7199_v5
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-7199-v5 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.03s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-7199-v5/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-7199-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-7199-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-7199-v5/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-7199-v5/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-7199-v5_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.74s
jellywibble-lora-120k-pr_7199_v5 status is now torndown due to DeploymentManager action