jellywibble-lora-120k-p_2801

developer_uid: Bbbrun0

submission_id: jellywibble-lora-120k-p_2801_v22

model_name: test_Jellywibble

model_group: Jellywibble/lora_120k_pr

status: torndown

timestamp: 2024-07-18T06:28:42+00:00

num_battles: 13833

num_wins: 8136

celo_rating: 1254.19

family_friendly_score: 0.0

submission_type: basic

model_repo: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment

model_architecture: LlamaForCausalLM

reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634

model_num_parameters: 8030261248.0

best_of: 16

max_input_tokens: 512

max_output_tokens: 64

display_name: test_Jellywibble

is_internal_developer: False

language_model: Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-17

win_ratio: 0.5881587508132726

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|end_header_id|>', '<|eot_id|>', '\n\n{user_name}'], '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-p-2801-v22-mkmlizer
Waiting for job on jellywibble-lora-120k-p-2801-v22-mkmlizer to finish
jellywibble-lora-120k-p-2801-v22-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║     _____            __           __                                ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║       /___/                                                         ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  Version: 0.9.5.post3                                               ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  https://mk1.ai                                                     ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  The license key for the current software has been verified as      ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  belonging to:                                                      ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  Chai Research Corp.                                                ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ║                                                                     ║
jellywibble-lora-120k-p-2801-v22-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jellywibble-lora-120k-p-2801-v22-mkmlizer: Downloaded to shared memory in 54.773s
jellywibble-lora-120k-p-2801-v22-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp0uoiqlao, device:0
jellywibble-lora-120k-p-2801-v22-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jellywibble-lora-120k-p-2801-v22-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:07, 39.39it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:04, 59.86it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:04, 67.39it/s]
Loading 0:  10%|▉         | 28/291 [00:00<00:03, 66.91it/s]
Loading 0:  12%|█▏        | 35/291 [00:00<00:09, 26.81it/s]
Loading 0:  14%|█▎        | 40/291 [00:01<00:08, 29.96it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:06, 38.98it/s]
Loading 0:  19%|█▊        | 54/291 [00:01<00:05, 43.34it/s]
Loading 0:  21%|██        | 60/291 [00:01<00:05, 45.56it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:04, 50.92it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:04, 52.40it/s]
Loading 0:  27%|██▋       | 80/291 [00:02<00:07, 28.00it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:06, 30.00it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:05, 35.30it/s]
Loading 0:  34%|███▍      | 99/291 [00:02<00:04, 43.99it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:03, 47.34it/s]
Loading 0:  38%|███▊      | 111/291 [00:02<00:03, 48.08it/s]
Loading 0:  42%|████▏     | 122/291 [00:02<00:02, 58.78it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:02, 59.29it/s]
Loading 0:  47%|████▋     | 136/291 [00:03<00:05, 30.54it/s]
Loading 0:  48%|████▊     | 141/291 [00:03<00:04, 32.77it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 38.90it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 45.51it/s]
Loading 0:  56%|█████▌    | 162/291 [00:03<00:02, 48.49it/s]
Loading 0:  58%|█████▊    | 168/291 [00:03<00:02, 49.25it/s]
Loading 0:  60%|██████    | 175/291 [00:04<00:02, 53.92it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:03, 34.04it/s]
Loading 0:  66%|██████▌   | 191/291 [00:04<00:02, 35.12it/s]
Loading 0:  67%|██████▋   | 196/291 [00:04<00:02, 36.18it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:02, 40.73it/s]
Loading 0:  72%|███████▏  | 210/291 [00:05<00:01, 48.87it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 53.45it/s]
Loading 0:  77%|███████▋  | 224/291 [00:05<00:01, 54.12it/s]
Loading 0:  79%|███████▉  | 230/291 [00:05<00:01, 55.04it/s]
Loading 0:  81%|████████  | 236/291 [00:05<00:01, 30.22it/s]
Loading 0:  83%|████████▎ | 241/291 [00:05<00:01, 32.47it/s]
Loading 0:  85%|████████▌ | 248/291 [00:06<00:01, 36.97it/s]
Loading 0:  88%|████████▊ | 256/291 [00:06<00:00, 45.53it/s]
Loading 0:  91%|█████████ | 264/291 [00:06<00:00, 52.99it/s]
Loading 0:  93%|█████████▎| 271/291 [00:06<00:00, 56.73it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 56.21it/s]
Loading 0:  98%|█████████▊| 286/291 [00:13<00:01,  3.25it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
jellywibble-lora-120k-p-2801-v22-mkmlizer: quantized model in 32.986s
jellywibble-lora-120k-p-2801-v22-mkmlizer: Processed model Jellywibble/lora_120k_pref_data_ep3_stacked_elo_alignment in 87.759s
jellywibble-lora-120k-p-2801-v22-mkmlizer: creating bucket guanaco-mkml-models
jellywibble-lora-120k-p-2801-v22-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jellywibble-lora-120k-p-2801-v22-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v22
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v22/special_tokens_map.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v22/config.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v22/tokenizer_config.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v22/tokenizer.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jellywibble-lora-120k-p-2801-v22/flywheel_model.0.safetensors
jellywibble-lora-120k-p-2801-v22-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
jellywibble-lora-120k-p-2801-v22-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:950: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-p-2801-v22-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v22-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:778: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
jellywibble-lora-120k-p-2801-v22-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v22-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.
jellywibble-lora-120k-p-2801-v22-mkmlizer:   warnings.warn(
jellywibble-lora-120k-p-2801-v22-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
jellywibble-lora-120k-p-2801-v22-mkmlizer: Saving duration: 2.380s
jellywibble-lora-120k-p-2801-v22-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 13.906s
jellywibble-lora-120k-p-2801-v22-mkmlizer: creating bucket guanaco-reward-models
jellywibble-lora-120k-p-2801-v22-mkmlizer: Bucket 's3://guanaco-reward-models/' created
jellywibble-lora-120k-p-2801-v22-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward/config.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward/special_tokens_map.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward/tokenizer_config.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward/merges.txt
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward/vocab.json
jellywibble-lora-120k-p-2801-v22-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/jellywibble-lora-120k-p-2801-v22_reward/tokenizer.json
Job jellywibble-lora-120k-p-2801-v22-mkmlizer completed after 139.43s with status: succeeded
Stopping job with name jellywibble-lora-120k-p-2801-v22-mkmlizer
Pipeline stage MKMLizer completed in 141.53s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service jellywibble-lora-120k-p-2801-v22
Waiting for inference service jellywibble-lora-120k-p-2801-v22 to be ready
Inference service jellywibble-lora-120k-p-2801-v22 ready after 40.929036140441895s
Pipeline stage ISVCDeployer completed in 43.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2761435508728027s
Received healthy response to inference request in 1.492311954498291s
Received healthy response to inference request in 1.4398844242095947s
Received healthy response to inference request in 1.4235055446624756s
Received healthy response to inference request in 1.492307186126709s
5 requests
0 failed requests
5th percentile: 1.4267813205718993
10th percentile: 1.4300570964813233
20th percentile: 1.436608648300171
30th percentile: 1.4503689765930177
40th percentile: 1.4713380813598633
50th percentile: 1.492307186126709
60th percentile: 1.4923090934753418
70th percentile: 1.4923110008239746
80th percentile: 1.6490782737731935
90th percentile: 1.9626109123229982
95th percentile: 2.1193772315979
99th percentile: 2.244790287017822
mean time: 1.6248305320739747
Pipeline stage StressChecker completed in 8.75s
jellywibble-lora-120k-p_2801_v22 status is now deployed due to DeploymentManager action
jellywibble-lora-120k-p_2801_v22 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of jellywibble-lora-120k-p_2801_v22
Running pipeline stage ISVCDeleter
Checking if service jellywibble-lora-120k-p-2801-v22 is running
Tearing down inference service jellywibble-lora-120k-p-2801-v22
Service jellywibble-lora-120k-p-2801-v22 has been torndown
Pipeline stage ISVCDeleter completed in 5.42s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-p-2801-v22/config.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v22/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v22/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v22/tokenizer.json from bucket guanaco-mkml-models
Deleting key jellywibble-lora-120k-p-2801-v22/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key jellywibble-lora-120k-p-2801-v22_reward/config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v22_reward/merges.txt from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v22_reward/reward.tensors from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v22_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v22_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v22_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key jellywibble-lora-120k-p-2801-v22_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.08s
jellywibble-lora-120k-p_2801_v22 status is now torndown due to DeploymentManager action