submission_id: trace2333-duduk-llama3-v2_v1
developer_uid: Trace2333
alignment_samples: 0
best_of: 16
celo_rating: 1164.06
display_name: trace2333-duduk-llama3-v2_v1
formatter: {'memory_template': "<|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\nYou: {message}<|eot_id|>', 'response_template': '<|start_header_id|>assistant<|end_header_id|>\n\n{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.15, 'top_p': 1.0, 'min_p': 0.15, 'top_k': 200, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64, 'reward_max_token_input': 256}
is_internal_developer: False
language_model: Trace2333/duduk_llama3_v2
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Trace2333/duduk_llama3_v
model_name: trace2333-duduk-llama3-v2_v1
model_num_parameters: 8030261248.0
model_repo: Trace2333/duduk_llama3_v2
model_size: 8B
num_battles: 20914
num_wins: 9236
propriety_score: 0.735195530726257
propriety_total_count: 895.0
ranking_group: single
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'}
reward_repo: Jellywibble/gpt2_xl_pairwise_89m_step_347634
status: torndown
submission_type: basic
timestamp: 2024-07-24T07:16:23+00:00
us_pacific_date: 2024-07-24
win_ratio: 0.4416180548914603
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name trace2333-duduk-llama3-v2-v1-mkmlizer
Waiting for job on trace2333-duduk-llama3-v2-v1-mkmlizer to finish
trace2333-duduk-llama3-v2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ _____ __ __ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ /___/ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ Version: 0.9.6 ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ https://mk1.ai ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ The license key for the current software has been verified as ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ belonging to: ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ Chai Research Corp. ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ║ ║
trace2333-duduk-llama3-v2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
trace2333-duduk-llama3-v2-v1-mkmlizer: Downloaded to shared memory in 61.620s
trace2333-duduk-llama3-v2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3c96ltm7, device:0
trace2333-duduk-llama3-v2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
trace2333-duduk-llama3-v2-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 2%|▏ | 5/291 [00:00<00:10, 28.12it/s] Loading 0: 4%|▍ | 12/291 [00:00<00:07, 37.61it/s] Loading 0: 5%|▌ | 16/291 [00:00<00:07, 35.69it/s] Loading 0: 7%|▋ | 21/291 [00:00<00:06, 39.29it/s] Loading 0: 9%|▉ | 26/291 [00:00<00:06, 38.94it/s] Loading 0: 11%|█ | 32/291 [00:00<00:06, 39.52it/s] Loading 0: 12%|█▏ | 36/291 [00:01<00:09, 26.04it/s] Loading 0: 14%|█▍ | 41/291 [00:01<00:09, 27.59it/s] Loading 0: 16%|█▋ | 48/291 [00:01<00:06, 34.72it/s] Loading 0: 18%|█▊ | 52/291 [00:01<00:07, 33.49it/s] Loading 0: 20%|█▉ | 57/291 [00:01<00:06, 35.60it/s] Loading 0: 21%|██ | 61/291 [00:01<00:06, 34.11it/s] Loading 0: 23%|██▎ | 66/291 [00:01<00:06, 36.66it/s] Loading 0: 24%|██▍ | 70/291 [00:02<00:06, 35.30it/s] Loading 0: 25%|██▌ | 74/291 [00:02<00:06, 35.26it/s] Loading 0: 27%|██▋ | 78/291 [00:02<00:06, 35.14it/s] Loading 0: 28%|██▊ | 82/291 [00:02<00:08, 24.10it/s] Loading 0: 30%|██▉ | 86/291 [00:02<00:07, 27.14it/s] Loading 0: 31%|███ | 90/291 [00:02<00:06, 29.01it/s] Loading 0: 32%|███▏ | 94/291 [00:02<00:06, 29.50it/s] Loading 0: 34%|███▍ | 99/291 [00:03<00:05, 32.76it/s] Loading 0: 35%|███▌ | 103/291 [00:03<00:05, 32.55it/s] Loading 0: 37%|███▋ | 108/291 [00:03<00:05, 35.91it/s] Loading 0: 38%|███▊ | 112/291 [00:03<00:05, 34.91it/s] Loading 0: 40%|███▉ | 116/291 [00:03<00:04, 35.36it/s] Loading 0: 42%|████▏ | 122/291 [00:03<00:04, 40.26it/s] Loading 0: 44%|████▎ | 127/291 [00:03<00:04, 38.19it/s] Loading 0: 46%|████▌ | 133/291 [00:04<00:04, 31.66it/s] Loading 0: 47%|████▋ | 137/291 [00:04<00:04, 32.19it/s] Loading 0: 48%|████▊ | 141/291 [00:04<00:04, 30.32it/s] Loading 0: 51%|█████ | 147/291 [00:04<00:04, 34.91it/s] Loading 0: 52%|█████▏ | 151/291 [00:04<00:04, 33.88it/s] Loading 0: 54%|█████▎ | 156/291 [00:04<00:03, 36.85it/s] Loading 0: 55%|█████▍ | 160/291 [00:04<00:03, 35.71it/s] Loading 0: 57%|█████▋ | 165/291 [00:04<00:03, 37.63it/s] Loading 0: 58%|█████▊ | 169/291 [00:05<00:03, 36.06it/s] Loading 0: 60%|█████▉ | 174/291 [00:05<00:03, 38.71it/s] Loading 0: 61%|██████ | 178/291 [00:05<00:03, 37.08it/s] Loading 0: 63%|██████▎ | 184/291 [00:05<00:02, 42.65it/s] Loading 0: 65%|██████▍ | 189/291 [00:05<00:03, 25.93it/s] Loading 0: 67%|██████▋ | 194/291 [00:05<00:03, 26.98it/s] Loading 0: 69%|██████▉ | 201/291 [00:05<00:02, 34.05it/s] Loading 0: 71%|███████ | 206/291 [00:06<00:02, 35.05it/s] Loading 0: 73%|███████▎ | 211/291 [00:06<00:02, 35.45it/s] Loading 0: 74%|███████▍ | 215/291 [00:06<00:02, 36.36it/s] Loading 0: 75%|███████▌ | 219/291 [00:06<00:01, 36.88it/s] Loading 0: 77%|███████▋ | 223/291 [00:06<00:01, 35.49it/s] Loading 0: 78%|███████▊ | 227/291 [00:06<00:01, 36.04it/s] Loading 0: 79%|███████▉ | 231/291 [00:06<00:01, 36.58it/s] Loading 0: 81%|████████ | 235/291 [00:07<00:02, 26.77it/s] Loading 0: 82%|████████▏ | 239/291 [00:07<00:01, 26.82it/s] Loading 0: 85%|████████▍ | 246/291 [00:07<00:01, 35.08it/s] Loading 0: 86%|████████▌ | 250/291 [00:07<00:01, 34.44it/s] Loading 0: 88%|████████▊ | 255/291 [00:07<00:00, 37.38it/s] Loading 0: 89%|████████▉ | 259/291 [00:07<00:00, 36.36it/s] Loading 0: 91%|█████████ | 264/291 [00:07<00:00, 39.08it/s] Loading 0: 92%|█████████▏| 269/291 [00:07<00:00, 38.72it/s] Loading 0: 94%|█████████▍| 274/291 [00:08<00:00, 38.58it/s] Loading 0: 96%|█████████▌| 279/291 [00:08<00:00, 40.74it/s] Loading 0: 98%|█████████▊| 284/291 [00:08<00:00, 41.59it/s] Loading 0: 99%|█████████▉| 289/291 [00:13<00:00, 2.81it/s] Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
trace2333-duduk-llama3-v2-v1-mkmlizer: quantized model in 27.979s
trace2333-duduk-llama3-v2-v1-mkmlizer: Processed model Trace2333/duduk_llama3_v2 in 89.599s
trace2333-duduk-llama3-v2-v1-mkmlizer: creating bucket guanaco-mkml-models
trace2333-duduk-llama3-v2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
trace2333-duduk-llama3-v2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v1
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v1/config.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v1/special_tokens_map.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v1/tokenizer_config.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v1/tokenizer.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/trace2333-duduk-llama3-v2-v1/flywheel_model.0.safetensors
trace2333-duduk-llama3-v2-v1-mkmlizer: loading reward model from Jellywibble/gpt2_xl_pairwise_89m_step_347634
trace2333-duduk-llama3-v2-v1-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.
trace2333-duduk-llama3-v2-v1-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v2-v1-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.
trace2333-duduk-llama3-v2-v1-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v2-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.
trace2333-duduk-llama3-v2-v1-mkmlizer: warnings.warn(
trace2333-duduk-llama3-v2-v1-mkmlizer: Saving duration: 1.361s
trace2333-duduk-llama3-v2-v1-mkmlizer: Processed model Jellywibble/gpt2_xl_pairwise_89m_step_347634 in 11.473s
trace2333-duduk-llama3-v2-v1-mkmlizer: creating bucket guanaco-reward-models
trace2333-duduk-llama3-v2-v1-mkmlizer: Bucket 's3://guanaco-reward-models/' created
trace2333-duduk-llama3-v2-v1-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/config.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/special_tokens_map.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/tokenizer_config.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/merges.txt
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/vocab.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/tokenizer.json
trace2333-duduk-llama3-v2-v1-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/trace2333-duduk-llama3-v2-v1_reward/reward.tensors
Retrying (%r) after connection broken by '%r': %s
Job trace2333-duduk-llama3-v2-v1-mkmlizer completed after 136.13s with status: succeeded
Stopping job with name trace2333-duduk-llama3-v2-v1-mkmlizer
Pipeline stage MKMLizer completed in 137.29s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service trace2333-duduk-llama3-v2-v1
Waiting for inference service trace2333-duduk-llama3-v2-v1 to be ready
Inference service trace2333-duduk-llama3-v2-v1 ready after 50.4933922290802s
Pipeline stage ISVCDeployer completed in 52.33s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.264685869216919s
Received healthy response to inference request in 1.4471228122711182s
Received healthy response to inference request in 1.3398172855377197s
Received healthy response to inference request in 1.4169437885284424s
Received healthy response to inference request in 1.3448481559753418s
5 requests
0 failed requests
5th percentile: 1.3408234596252442
10th percentile: 1.3418296337127686
20th percentile: 1.3438419818878173
30th percentile: 1.359267282485962
40th percentile: 1.388105535507202
50th percentile: 1.4169437885284424
60th percentile: 1.4290153980255127
70th percentile: 1.441087007522583
80th percentile: 1.6106354236602785
90th percentile: 1.9376606464385988
95th percentile: 2.1011732578277584
99th percentile: 2.231983346939087
mean time: 1.5626835823059082
Pipeline stage StressChecker completed in 8.79s
trace2333-duduk-llama3-v2_v1 status is now deployed due to DeploymentManager action
Failed to get response for submission undi95-meta-llama-3-70b_6209_v18: ('http://undi95-meta-llama-3-70b-6209-v18-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"TypeError : SamplingParameters.__init__() got an unexpected keyword argument \'reward_max_tokens\'"}')
trace2333-duduk-llama3-v2_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of trace2333-duduk-llama3-v2_v1
Running pipeline stage ISVCDeleter
Checking if service trace2333-duduk-llama3-v2-v1 is running
Tearing down inference service trace2333-duduk-llama3-v2-v1
Service trace2333-duduk-llama3-v2-v1 has been torndown
Pipeline stage ISVCDeleter completed in 4.90s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v2-v1/config.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key trace2333-duduk-llama3-v2-v1/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key trace2333-duduk-llama3-v2-v1_reward/config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v1_reward/merges.txt from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v1_reward/reward.tensors from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v1_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v1_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v1_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key trace2333-duduk-llama3-v2-v1_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 6.30s
trace2333-duduk-llama3-v2_v1 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics