chaiml-elo-alignment-run-3

developer_uid: zonemercy

submission_id: chaiml-elo-alignment-run-3_v2

model_name: dpo-v2-0710-rm-score-completed

model_group: ChaiML/elo_alignment_run

status: torndown

timestamp: 2024-07-12T12:58:14+00:00

num_battles: 18961

num_wins: 11601

celo_rating: 1269.92

family_friendly_score: 0.0

submission_type: basic

model_repo: ChaiML/elo_alignment_run_3

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: dpo-v2-0710-rm-score-completed

is_internal_developer: True

language_model: ChaiML/elo_alignment_run_3

model_size: 8B

ranking_group: single

us_pacific_date: 2024-07-12

win_ratio: 0.6118348188386689

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 chaiml-elo-alignment-run-3-v2-mkmlizer
Waiting for job on chaiml-elo-alignment-run-3-v2-mkmlizer to finish
chaiml-elo-alignment-run-3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-elo-alignment-run-3-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║       /___/                                                         ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  Version: 0.8.14                                                    ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ║                                                                     ║
chaiml-elo-alignment-run-3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-elo-alignment-run-3-v2-mkmlizer: Downloaded to shared memory in 52.330s
chaiml-elo-alignment-run-3-v2-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-elo-alignment-run-3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-elo-alignment-run-3-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:06, 43.68it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:04, 58.56it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:04, 63.06it/s]
Loading 0:  11%|█▏        | 33/291 [00:00<00:07, 36.17it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:06, 38.31it/s]
Loading 0:  15%|█▍        | 43/291 [00:01<00:06, 40.03it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:05, 43.61it/s]
Loading 0:  20%|█▉        | 58/291 [00:01<00:04, 52.00it/s]
Loading 0:  23%|██▎       | 67/291 [00:01<00:03, 56.92it/s]
Loading 0:  26%|██▌       | 75/291 [00:01<00:03, 58.03it/s]
Loading 0:  28%|██▊       | 82/291 [00:01<00:06, 33.49it/s]
Loading 0:  31%|███▏      | 91/291 [00:02<00:04, 40.59it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:04, 46.46it/s]
Loading 0:  37%|███▋      | 108/291 [00:02<00:03, 52.91it/s]
Loading 0:  40%|███▉      | 115/291 [00:02<00:03, 56.34it/s]
Loading 0:  43%|████▎     | 125/291 [00:02<00:02, 61.74it/s]
Loading 0:  46%|████▌     | 133/291 [00:03<00:04, 36.15it/s]
Loading 0:  48%|████▊     | 139/291 [00:03<00:04, 37.50it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 44.16it/s]
Loading 0:  54%|█████▍    | 157/291 [00:03<00:02, 49.48it/s]
Loading 0:  57%|█████▋    | 166/291 [00:03<00:02, 54.22it/s]
Loading 0:  60%|██████    | 175/291 [00:03<00:02, 57.99it/s]
Loading 0:  64%|██████▍   | 186/291 [00:04<00:02, 40.12it/s]
Loading 0:  66%|██████▌   | 192/291 [00:04<00:02, 38.91it/s]
Loading 0:  69%|██████▉   | 201/291 [00:04<00:02, 44.85it/s]
Loading 0:  72%|███████▏  | 210/291 [00:04<00:01, 50.14it/s]
Loading 0:  75%|███████▌  | 219/291 [00:04<00:01, 54.62it/s]
Loading 0:  78%|███████▊  | 227/291 [00:04<00:01, 56.17it/s]
Loading 0:  80%|████████  | 234/291 [00:05<00:01, 34.30it/s]
Loading 0:  82%|████████▏ | 239/291 [00:05<00:01, 36.47it/s]
Loading 0:  85%|████████▌ | 248/291 [00:05<00:00, 43.77it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 47.13it/s]
Loading 0:  91%|█████████ | 264/291 [00:05<00:00, 53.48it/s]
Loading 0:  94%|█████████▍| 273/291 [00:05<00:00, 56.95it/s]
Loading 0:  97%|█████████▋| 281/291 [00:05<00:00, 57.69it/s]
Loading 0:  99%|█████████▉| 288/291 [00:12<00:00,  3.59it/s]
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
chaiml-elo-alignment-run-3-v2-mkmlizer: quantized model in 31.556s
chaiml-elo-alignment-run-3-v2-mkmlizer: Processed model ChaiML/elo_alignment_run_3 in 83.887s
chaiml-elo-alignment-run-3-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-elo-alignment-run-3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-elo-alignment-run-3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v2
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v2/special_tokens_map.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v2/tokenizer_config.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v2/config.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v2/tokenizer.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-elo-alignment-run-3-v2/flywheel_model.0.safetensors
chaiml-elo-alignment-run-3-v2-mkmlizer: loading reward model from ChaiML/gpt2_xl_pairwise_89m_step_347634
chaiml-elo-alignment-run-3-v2-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.
chaiml-elo-alignment-run-3-v2-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v2-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`.
chaiml-elo-alignment-run-3-v2-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v2-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.
chaiml-elo-alignment-run-3-v2-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v2-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.
chaiml-elo-alignment-run-3-v2-mkmlizer:   warnings.warn(
chaiml-elo-alignment-run-3-v2-mkmlizer: 
Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]
Downloading shards:  50%|█████     | 1/2 [00:06<00:06,  6.99s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.21s/it]
Downloading shards: 100%|██████████| 2/2 [00:09<00:00,  4.63s/it]
chaiml-elo-alignment-run-3-v2-mkmlizer: 
Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|█████     | 1/2 [00:00<00:00,  1.63it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.69it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:00<00:00,  2.45it/s]
chaiml-elo-alignment-run-3-v2-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-elo-alignment-run-3-v2-mkmlizer: Saving duration: 2.188s
chaiml-elo-alignment-run-3-v2-mkmlizer: Processed model ChaiML/gpt2_xl_pairwise_89m_step_347634 in 14.837s
chaiml-elo-alignment-run-3-v2-mkmlizer: creating bucket guanaco-reward-models
chaiml-elo-alignment-run-3-v2-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-elo-alignment-run-3-v2-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/config.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/tokenizer_config.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/merges.txt
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/special_tokens_map.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/vocab.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/tokenizer.json
chaiml-elo-alignment-run-3-v2-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-elo-alignment-run-3-v2_reward/reward.tensors
Job chaiml-elo-alignment-run-3-v2-mkmlizer completed after 124.36s with status: succeeded
Stopping job with name chaiml-elo-alignment-run-3-v2-mkmlizer
Pipeline stage MKMLizer completed in 125.32s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.10s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-elo-alignment-run-3-v2
Waiting for inference service chaiml-elo-alignment-run-3-v2 to be ready
Inference service chaiml-elo-alignment-run-3-v2 ready after 50.228535175323486s
Pipeline stage ISVCDeployer completed in 57.14s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.352778673171997s
Received healthy response to inference request in 1.574326515197754s
Received healthy response to inference request in 1.5319807529449463s
Received healthy response to inference request in 1.5183327198028564s
Received healthy response to inference request in 1.5663609504699707s
5 requests
0 failed requests
5th percentile: 1.5210623264312744
10th percentile: 1.5237919330596923
20th percentile: 1.5292511463165284
30th percentile: 1.5388567924499512
40th percentile: 1.5526088714599608
50th percentile: 1.5663609504699707
60th percentile: 1.569547176361084
70th percentile: 1.5727334022521973
80th percentile: 1.7300169467926028
90th percentile: 2.0413978099823
95th percentile: 2.1970882415771484
99th percentile: 2.3216405868530274
mean time: 1.7087559223175048
Pipeline stage StressChecker completed in 9.19s
chaiml-elo-alignment-run-3_v2 status is now deployed due to DeploymentManager action
chaiml-elo-alignment-run-3_v2 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-elo-alignment-run-3_v2
Running pipeline stage ISVCDeleter
Checking if service chaiml-elo-alignment-run-3-v2 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.64s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v2/config.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-elo-alignment-run-3-v2/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-elo-alignment-run-3-v2_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v2_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v2_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v2_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v2_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v2_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-elo-alignment-run-3-v2_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 5.49s
chaiml-elo-alignment-run-3_v2 status is now torndown due to DeploymentManager action