asap-zzhou

Asap-zzhou's group workspace

Group: alpaca-ablations

1-3

of 3

Tags

Notes

Author

asap-zzhou

State

Finished

Start time

October 30th, 2025 12:58:07 AM

Runtime

8m 34s

Tracked hours

8m 31s

Run path

asap-zzhou/dllm/5kq65gdg

Linux-3.10.0-957.el7.x86_64-x86_64-with-glibc2.17

Python version

CPython 3.10.18

Git repository

git clone git@github.com:ZHZisZZ/dllm.git

Git state

git checkout -b "ModernBERT-large/alpaca/openwebtext/epochs-20-bs-512-len-512" df67f70cb557ab2459fc53a3049a414578c1fe2d

Command

/mnt/lustrenew/mllm_aligned/dongzhichen/dllm/examples/bert/sft.py --model_name_or_path models/ModernBERT-large/openwebtext/steps-200000-bs-1024-len-1024/checkpoint-18000 --dataset_args tatsu-lab/alpaca --max_length 512 --num_train_epochs 20 --per_device_train_batch_size 64 --per_device_eval_batch_size 64 --save_steps 0.1 --output_dir models/ModernBERT-large/alpaca/openwebtext/epochs-20-bs-512-len-512

System Hardware

CPU count	64
Logical CPU count	128
GPU count	8
GPU type	NVIDIA A100-SXM4-80GB

W&B CLI Version

0.22.2

Group

alpaca-ablations

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 219 keys
- _name_or_path:
  "models/ModernBERT-large/openwebtext/steps-200000-bs-1024-len-1024/checkpoint-18000"
- ▶
  accelerator_config:{} 6 keys
- adafactor:
  false
- adam_beta1:
  0.9
- adam_beta2:
  0.999
- adam_epsilon:
  0.00000001
- add_cross_attention:
  false
- ▶
  architectures:[] 1 item
  - 0:
    "ModernBertForMaskedLM"
- attention_bias:
  false
- attention_dropout:
  0
- auto_find_batch_size:
  false
- average_tokens_across_devices:
  true
- bad_words_ids:
  null
- batch_eval_metrics:
  false
- begin_suppress_tokens:
  null
- bf16:
  true
- bf16_full_eval:
  false
- bos_token_id:
  null
- chunk_size_feed_forward:
  0
- classifier_activation:
  "gelu"
- classifier_bias:
  false
- classifier_dropout:
  0
- classifier_pooling:
  "mean"
- cls_token_id:
  50,281
- cross_attention_hidden_size:
  null
- data_seed:
  null
- dataloader_drop_last:
  false
- dataloader_num_workers:
  0
- dataloader_persistent_workers:
  false
- dataloader_pin_memory:
  true
- dataloader_prefetch_factor:
  null
- ddp_backend:
  null
- ddp_broadcast_buffers:
  null
- ddp_bucket_cap_mb:
  null
- ddp_find_unused_parameters:
  null
- ddp_timeout:
  1,800
- debug:[] 0 items
- decoder_bias:
  true
- decoder_start_token_id:
  null
- deepspeed:
  null
- deterministic_flash_attn:
  false
- disable_tqdm:
  false
- diversity_penalty:
  0
- do_eval:
  true
- do_predict:
  false
- do_sample:
  false
- vocab_size:
  50,368
- warmup_ratio:
  0.1
- warmup_steps:
  0
- weight_decay:
  0

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 14 keys
- eval/loss:
  1.3181915283203125
- eval/runtime:
  1.3886
- eval/samples_per_second:
  3,745.409
- eval/steps_per_second:
  7.921
- total_flos:
  198,651,305,726,574,592
- train_loss:
  1.331548237800598
- train_runtime:
  512.3445
- train_samples_per_second:
  1,826.896
- train_steps_per_second:
  3.591
- train/epoch:
  20
- train/global_step:
  1,840
- train/grad_norm:
  0.96875
- train/learning_rate:
  0.00000000008997439994
- train/loss:
  1.2008

This run produced these artifacts as outputs. Total: 1. Learn more

wandb-history

run-5kq65gdg-history:v0