cycy233-l3-s-a-v0-c1

developer_uid: shiroe40

submission_id: cycy233-l3-s-a-v0-c1_v1

model_name: auto

model_group: cycy233/L3-s-a-v0-c1

status: torndown

timestamp: 2024-08-08T02:18:20+00:00

num_battles: 10605

num_wins: 5614

celo_rating: 1229.76

family_friendly_score: 0.0

submission_type: basic

model_repo: cycy233/L3-s-a-v0-c1

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: auto

is_internal_developer: False

language_model: cycy233/L3-s-a-v0-c1

model_size: 8B

ranking_group: single

us_pacific_date: 2024-08-07

win_ratio: 0.5293729372937294

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|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}

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 cycy233-l3-s-a-v0-c1-v1-mkmlizer
Waiting for job on cycy233-l3-s-a-v0-c1-v1-mkmlizer to finish
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║     _____            __           __                                ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║       /___/                                                         ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  Version: 0.9.9                                                     ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  belonging to:                                                      ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ║                                                                     ║
cycy233-l3-s-a-v0-c1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Downloaded to shared memory in 31.345s
cycy233-l3-s-a-v0-c1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptjrv3_nm, device:0
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-s-a-v0-c1-v1-mkmlizer: quantized model in 26.616s
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Processed model cycy233/L3-s-a-v0-c1 in 57.961s
cycy233-l3-s-a-v0-c1-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-s-a-v0-c1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-s-a-v0-c1-v1
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-s-a-v0-c1-v1/config.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-s-a-v0-c1-v1/special_tokens_map.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-s-a-v0-c1-v1/tokenizer_config.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-s-a-v0-c1-v1/tokenizer.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-s-a-v0-c1-v1/flywheel_model.0.safetensors
cycy233-l3-s-a-v0-c1-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-s-a-v0-c1-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:08, 34.84it/s]
Loading 0:   4%|▍         | 13/291 [00:00<00:05, 54.62it/s]
Loading 0:   7%|▋         | 19/291 [00:00<00:05, 47.38it/s]
Loading 0:   8%|▊         | 24/291 [00:00<00:05, 48.03it/s]
Loading 0:  11%|█         | 32/291 [00:00<00:05, 48.76it/s]
Loading 0:  14%|█▍        | 41/291 [00:00<00:04, 51.00it/s]
Loading 0:  17%|█▋        | 49/291 [00:00<00:04, 58.00it/s]
Loading 0:  19%|█▉        | 56/291 [00:01<00:04, 55.24it/s]
Loading 0:  21%|██▏       | 62/291 [00:01<00:04, 54.03it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:04, 46.49it/s]
Loading 0:  26%|██▌       | 76/291 [00:01<00:04, 52.37it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:04, 49.19it/s]
Loading 0:  30%|███       | 88/291 [00:01<00:05, 35.08it/s]
Loading 0:  32%|███▏      | 94/291 [00:02<00:05, 39.38it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 39.75it/s]
Loading 0:  36%|███▌      | 105/291 [00:02<00:04, 40.73it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 46.38it/s]
Loading 0:  41%|████      | 118/291 [00:02<00:03, 43.78it/s]
Loading 0:  42%|████▏     | 123/291 [00:02<00:03, 43.07it/s]
Loading 0:  44%|████▍     | 129/291 [00:02<00:03, 46.63it/s]
Loading 0:  46%|████▌     | 134/291 [00:02<00:03, 46.96it/s]
Loading 0:  48%|████▊     | 139/291 [00:02<00:03, 47.40it/s]
Loading 0:  50%|████▉     | 145/291 [00:03<00:03, 44.43it/s]
Loading 0:  52%|█████▏    | 150/291 [00:03<00:03, 44.69it/s]
Loading 0:  54%|█████▎    | 156/291 [00:03<00:02, 48.65it/s]
Loading 0:  55%|█████▌    | 161/291 [00:03<00:02, 48.52it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 48.16it/s]
Loading 0:  59%|█████▉    | 172/291 [00:03<00:02, 44.84it/s]
Loading 0:  62%|██████▏   | 179/291 [00:03<00:02, 48.33it/s]
Loading 0:  63%|██████▎   | 184/291 [00:04<00:02, 39.23it/s]
Loading 0:  65%|██████▍   | 189/291 [00:04<00:03, 27.14it/s]
Loading 0:  67%|██████▋   | 194/291 [00:04<00:03, 29.79it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 36.22it/s]
Loading 0:  71%|███████   | 206/291 [00:04<00:02, 37.93it/s]
Loading 0:  73%|███████▎  | 211/291 [00:04<00:02, 39.66it/s]
Loading 0:  75%|███████▍  | 217/291 [00:05<00:01, 38.71it/s]
Loading 0:  76%|███████▋  | 222/291 [00:05<00:01, 39.59it/s]
Loading 0:  79%|███████▊  | 229/291 [00:05<00:01, 45.57it/s]
Loading 0:  81%|████████  | 235/291 [00:05<00:01, 42.74it/s]
Loading 0:  82%|████████▏ | 240/291 [00:05<00:01, 42.46it/s]
Loading 0:  85%|████████▍ | 246/291 [00:05<00:00, 46.48it/s]
Loading 0:  86%|████████▋ | 251/291 [00:05<00:00, 46.59it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 46.67it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 42.73it/s]
Loading 0:  92%|█████████▏| 267/291 [00:06<00:00, 42.22it/s]
Loading 0:  94%|█████████▍| 273/291 [00:06<00:00, 46.30it/s]
Loading 0:  96%|█████████▌| 278/291 [00:06<00:00, 46.05it/s]
Loading 0:  97%|█████████▋| 283/291 [00:06<00:00, 37.51it/s]
Loading 0:  99%|█████████▉| 288/291 [00:11<00:00,  3.03it/s]
                                                            
/opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:957: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-s-a-v0-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-s-a-v0-c1-v1-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:785: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
cycy233-l3-s-a-v0-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-s-a-v0-c1-v1-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.
cycy233-l3-s-a-v0-c1-v1-mkmlizer:   warnings.warn(
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Saving duration: 1.405s
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.556s
cycy233-l3-s-a-v0-c1-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-s-a-v0-c1-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-s-a-v0-c1-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-s-a-v0-c1-v1_reward
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-s-a-v0-c1-v1_reward/config.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-s-a-v0-c1-v1_reward/special_tokens_map.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-s-a-v0-c1-v1_reward/tokenizer_config.json
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-s-a-v0-c1-v1_reward/merges.txt
cycy233-l3-s-a-v0-c1-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/cycy233-l3-s-a-v0-c1-v1_reward/reward.tensors
Job cycy233-l3-s-a-v0-c1-v1-mkmlizer completed after 106.42s with status: succeeded
Stopping job with name cycy233-l3-s-a-v0-c1-v1-mkmlizer
Pipeline stage MKMLizer completed in 107.50s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.13s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-s-a-v0-c1-v1
Waiting for inference service cycy233-l3-s-a-v0-c1-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission cycy233-l3-s-a-v0-c3_v1: ('http://cycy233-l3-s-a-v0-c3-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service cycy233-l3-s-a-v0-c1-v1 ready after 191.36048436164856s
Pipeline stage ISVCDeployer completed in 193.00s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3762247562408447s
Received healthy response to inference request in 1.4767656326293945s
Received healthy response to inference request in 1.487288475036621s
Received healthy response to inference request in 1.4524846076965332s
Received healthy response to inference request in 1.5100793838500977s
5 requests
0 failed requests
5th percentile: 1.4573408126831056
10th percentile: 1.4621970176696777
20th percentile: 1.4719094276428222
30th percentile: 1.4788702011108399
40th percentile: 1.4830793380737304
50th percentile: 1.487288475036621
60th percentile: 1.4964048385620117
70th percentile: 1.5055212020874023
80th percentile: 1.6833084583282472
90th percentile: 2.029766607284546
95th percentile: 2.2029956817626952
99th percentile: 2.341578941345215
mean time: 1.6605685710906983
Pipeline stage StressChecker completed in 9.01s
cycy233-l3-s-a-v0-c1_v1 status is now deployed due to DeploymentManager action
cycy233-l3-s-a-v0-c1_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of cycy233-l3-s-a-v0-c1_v1
Running pipeline stage ISVCDeleter
Checking if service cycy233-l3-s-a-v0-c1-v1 is running
Tearing down inference service cycy233-l3-s-a-v0-c1-v1
Service cycy233-l3-s-a-v0-c1-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.58s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key cycy233-l3-s-a-v0-c1-v1/config.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-a-v0-c1-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-a-v0-c1-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-a-v0-c1-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key cycy233-l3-s-a-v0-c1-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key cycy233-l3-s-a-v0-c1-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.19s
cycy233-l3-s-a-v0-c1_v1 status is now torndown due to DeploymentManager action