jellywibble-lora-120k-pr_2801

developer_uid: zonemercy

submission_id: jellywibble-lora-120k-pr_2801_v6

model_name: jellywibble-lora-120k-pr_2801_v6

model_group: Jellywibble/lora_120k_pr

status: torndown

timestamp: 2024-07-12T16:12:01+00:00

num_battles: 11193

num_wins: 6969

celo_rating: 1262.03

family_friendly_score: 0.0

submission_type: basic

model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment

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: jellywibble-lora-120k-pr_2801_v6

is_internal_developer: True

language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-12

win_ratio: 0.6226212811578665

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-2801-v6-mkmlizer
Waiting for job on jellywibble-lora-120k-pr-2801-v6-mkmlizer to finish
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  Version: 0.8.14                                                    ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-pr-2801-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Downloaded to shared memory in 49.009s
jellywibble-lora-120k-pr-2801-v6-mkmlizer: quantizing model to /dev/shm/model_cache
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-pr-2801-v6-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 45.03it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 59.17it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 63.15it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:07, 36.21it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:06, 38.30it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:06, 39.99it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 44.02it/s]
Loading 0:  20%|██        | 59/291 [00:01<00:04, 50.99it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:03, 55.89it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:03, 61.62it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:06, 33.25it/s]
Loading 0:  32%|███▏      | 92/291 [00:02<00:04, 40.27it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 47.22it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 53.52it/s]
Loading 0:  40%|███▉      | 116/291 [00:02<00:03, 55.46it/s]
Loading 0:  43%|████▎     | 126/291 [00:02<00:02, 60.86it/s]
Loading 0:  46%|████▌     | 133/291 [00:02<00:04, 35.73it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:04, 36.39it/s]
Loading 0:  51%|█████     | 147/291 [00:03<00:03, 42.97it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 47.77it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 44.86it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 46.99it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 51.72it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 35.70it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 37.28it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 38.60it/s]
Loading 0:  70%|██████▉   | 203/291 [00:04<00:02, 42.38it/s]
Loading 0:  73%|███████▎  | 212/291 [00:04<00:01, 49.15it/s]
Loading 0:  76%|███████▌  | 221/291 [00:04<00:01, 54.00it/s]
Loading 0:  78%|███████▊  | 228/291 [00:04<00:01, 57.59it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 33.74it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 33.73it/s]
Loading 0:  85%|████████▍ | 247/291 [00:05<00:01, 39.85it/s]
Loading 0:  88%|████████▊ | 255/291 [00:05<00:00, 47.89it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 52.75it/s]
Loading 0:  92%|█████████▏| 269/291 [00:05<00:00, 53.45it/s]
Loading 0:  95%|█████████▍| 276/291 [00:06<00:00, 53.36it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  3.63it/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-v6-mkmlizer: quantized model in 31.835s
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 80.844s
jellywibble-lora-120k-pr-2801-v6-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-pr-2801-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v6
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v6/config.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v6/special_tokens_map.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v6/tokenizer_config.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v6/tokenizer.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-pr-2801-v6/flywheel_model.0.safetensors
jellywibble-lora-120k-pr-2801-v6-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-pr-2801-v6-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-v6-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v6-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-v6-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v6-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-v6-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v6-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-v6-mkmlizer:   warnings.warn(
jellywibble-lora-120k-pr-2801-v6-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.64s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.81s/it]
Downloading shards: 100%|██████████| 2/2 [00:11<00:00,  5.93s/it]
jellywibble-lora-120k-pr-2801-v6-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.68it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.73it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.50it/s]
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Saving duration: 2.138s
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 16.237s
jellywibble-lora-120k-pr-2801-v6-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-pr-2801-v6-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-pr-2801-v6-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/config.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/tokenizer_config.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/special_tokens_map.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/vocab.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/merges.txt
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/tokenizer.json
jellywibble-lora-120k-pr-2801-v6-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/jellywibble-lora-120k-pr-2801-v6_reward/reward.tensors
Job jellywibble-lora-120k-pr-2801-v6-mkmlizer completed after 124.74s with status: succeeded
Stopping job with name jellywibble-lora-120k-pr-2801-v6-mkmlizer
Pipeline stage MKMLizer completed in 125.46s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-pr-2801-v6
Waiting for inference service jellywibble-lora-120k-pr-2801-v6 to be ready
Inference service jellywibble-lora-120k-pr-2801-v6 ready after 40.30546188354492s
Pipeline stage ISVCDeployer completed in 47.16s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.287712574005127s
Received healthy response to inference request in 1.5972533226013184s
Received healthy response to inference request in 1.564368486404419s
Received healthy response to inference request in 1.5457868576049805s
Received healthy response to inference request in 1.617678165435791s
5 requests
0 failed requests
5th percentile: 1.5495031833648683
10th percentile: 1.5532195091247558
20th percentile: 1.5606521606445312
30th percentile: 1.5709454536437988
40th percentile: 1.5840993881225587
50th percentile: 1.5972533226013184
60th percentile: 1.6054232597351075
70th percentile: 1.6135931968688966
80th percentile: 1.7516850471496583
90th percentile: 2.0196988105773928
95th percentile: 2.15370569229126
99th percentile: 2.2609111976623537
mean time: 1.722559881210327
Pipeline stage StressChecker completed in 9.28s
jellywibble-lora-120k-pr_2801_v6 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-pr_2801_v6 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-pr_2801_v6
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-pr-2801-v6 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.59s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2801-v6/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v6/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v6/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v6/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-pr-2801-v6/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-pr-2801-v6_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.43s
jellywibble-lora-120k-pr_2801_v6 status is now torndown due to DeploymentManager action