developer_uid: shiroe40
submission_id: cycy233-l3-ss-v0-c3_v1
model_name: auto
model_group: cycy233/L3-ss-v0-c3
status: torndown
timestamp: 2024-08-13T02:24:16+00:00
num_battles: 10427
num_wins: 4935
celo_rating: 1194.16
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/L3-ss-v0-c3
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-ss-v0-c3
model_size: 8B
ranking_group: single
us_pacific_date: 2024-08-12
win_ratio: 0.4732904958281385
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': ['<|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-ss-v0-c3-v1-mkmlizer
Waiting for job on cycy233-l3-ss-v0-c3-v1-mkmlizer to finish
cycy233-l3-ss-v0-c3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ _____ __ __ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ /___/ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ Version: 0.9.9 ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ https://mk1.ai ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ The license key for the current software has been verified as ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ belonging to: ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ Chai Research Corp. ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ║ ║
cycy233-l3-ss-v0-c3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-l3-ss-v0-c3-v1-mkmlizer: Downloaded to shared memory in 31.502s
cycy233-l3-ss-v0-c3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp28cqwfre, device:0
cycy233-l3-ss-v0-c3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-l3-ss-v0-c3-v1-mkmlizer: quantized model in 27.243s
cycy233-l3-ss-v0-c3-v1-mkmlizer: Processed model cycy233/L3-ss-v0-c3 in 58.746s
cycy233-l3-ss-v0-c3-v1-mkmlizer: creating bucket guanaco-mkml-models
cycy233-l3-ss-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-l3-ss-v0-c3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-l3-ss-v0-c3-v1
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c3-v1/special_tokens_map.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c3-v1/config.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c3-v1/tokenizer_config.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-l3-ss-v0-c3-v1/tokenizer.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cycy233-l3-ss-v0-c3-v1/flywheel_model.0.safetensors
cycy233-l3-ss-v0-c3-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
cycy233-l3-ss-v0-c3-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%|▏ | 4/291 [00:00<00:08, 34.82it/s] Loading 0: 4%|▍ | 13/291 [00:00<00:05, 51.35it/s] Loading 0: 8%|▊ | 22/291 [00:00<00:04, 56.72it/s] Loading 0: 11%|█ | 31/291 [00:00<00:04, 57.53it/s] Loading 0: 14%|█▎ | 40/291 [00:00<00:04, 58.34it/s] Loading 0: 17%|█▋ | 49/291 [00:00<00:04, 59.93it/s] Loading 0: 20%|█▉ | 58/291 [00:00<00:03, 61.42it/s] Loading 0: 23%|██▎ | 67/291 [00:01<00:03, 61.75it/s] Loading 0: 26%|██▌ | 76/291 [00:01<00:03, 61.90it/s] Loading 0: 29%|██▊ | 83/291 [00:02<00:11, 18.34it/s] Loading 0: 30%|███ | 88/291 [00:02<00:09, 20.99it/s] Loading 0: 33%|███▎ | 97/291 [00:02<00:06, 28.58it/s] Loading 0: 36%|███▋ | 106/291 [00:02<00:05, 36.66it/s] Loading 0: 40%|███▉ | 115/291 [00:02<00:03, 44.87it/s] Loading 0: 45%|████▍ | 130/291 [00:03<00:02, 59.44it/s] Loading 0: 48%|████▊ | 139/291 [00:03<00:02, 62.89it/s] Loading 0: 52%|█████▏ | 151/291 [00:03<00:02, 68.74it/s] Loading 0: 57%|█████▋ | 166/291 [00:03<00:01, 78.37it/s] Loading 0: 60%|██████ | 175/291 [00:03<00:01, 78.20it/s] Loading 0: 63%|██████▎ | 184/291 [00:03<00:01, 76.63it/s] Loading 0: 66%|██████▋ | 193/291 [00:04<00:04, 21.62it/s] Loading 0: 69%|██████▉ | 202/291 [00:05<00:03, 26.84it/s] Loading 0: 73%|███████▎ | 211/291 [00:05<00:02, 33.13it/s] Loading 0: 76%|███████▌ | 220/291 [00:05<00:01, 39.90it/s] Loading 0: 79%|███████▊ | 229/291 [00:05<00:01, 46.27it/s] Loading 0: 82%|████████▏ | 238/291 [00:05<00:01, 52.46it/s] Loading 0: 85%|████████▍ | 247/291 [00:05<00:00, 57.68it/s] Loading 0: 88%|████████▊ | 256/291 [00:05<00:00, 61.46it/s] Loading 0: 91%|█████████ | 265/291 [00:05<00:00, 63.45it/s] Loading 0: 94%|█████████▍| 274/291 [00:05<00:00, 65.32it/s] Loading 0: 97%|█████████▋| 283/291 [00:06<00:00, 70.31it/s] Loading 0: 100%|██████████| 291/291 [00:11<00:00, 5.07it/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-ss-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-v0-c3-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-ss-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-v0-c3-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-ss-v0-c3-v1-mkmlizer: warnings.warn(
cycy233-l3-ss-v0-c3-v1-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
cycy233-l3-ss-v0-c3-v1-mkmlizer: Saving duration: 1.428s
cycy233-l3-ss-v0-c3-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.406s
cycy233-l3-ss-v0-c3-v1-mkmlizer: creating bucket guanaco-reward-models
cycy233-l3-ss-v0-c3-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
cycy233-l3-ss-v0-c3-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward/config.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward/special_tokens_map.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward/tokenizer_config.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward/merges.txt
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward/vocab.json
cycy233-l3-ss-v0-c3-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/cycy233-l3-ss-v0-c3-v1_reward/tokenizer.json
Job cycy233-l3-ss-v0-c3-v1-mkmlizer completed after 104.71s with status: succeeded
Stopping job with name cycy233-l3-ss-v0-c3-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.55s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.11s
Running pipeline stage ISVCDeployer
Creating inference service cycy233-l3-ss-v0-c3-v1
Waiting for inference service cycy233-l3-ss-v0-c3-v1 to be ready
Inference service cycy233-l3-ss-v0-c3-v1 ready after 211.2808961868286s
Pipeline stage ISVCDeployer completed in 213.15s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.423382043838501s
Received healthy response to inference request in 1.5920026302337646s
Received healthy response to inference request in 1.4950971603393555s
Received healthy response to inference request in 1.4811255931854248s
Received healthy response to inference request in 1.5947277545928955s
5 requests
0 failed requests
5th percentile: 1.483919906616211
10th percentile: 1.4867142200469972
20th percentile: 1.4923028469085693
30th percentile: 1.5144782543182373
40th percentile: 1.5532404422760009
50th percentile: 1.5920026302337646
60th percentile: 1.593092679977417
70th percentile: 1.5941827297210693
80th percentile: 1.7604586124420167
90th percentile: 2.091920328140259
95th percentile: 2.2576511859893795
99th percentile: 2.3902358722686765
mean time: 1.7172670364379883
Pipeline stage StressChecker completed in 9.30s
cycy233-l3-ss-v0-c3_v1 status is now deployed due to DeploymentManager action
cycy233-l3-ss-v0-c3_v1 status is now inactive due to auto deactivation removed underperforming models
cycy233-l3-ss-v0-c3_v1 status is now torndown due to DeploymentManager action