| { | |
| "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.17", | |
| "python": "3.8.10", | |
| "heartbeatAt": "2021-07-09T14:14:47.469719", | |
| "startedAt": "2021-07-09T14:14:45.370847", | |
| "docker": null, | |
| "cpu_count": 96, | |
| "cuda": null, | |
| "args": [ | |
| "--output_dir=/home/cahya/Work/flax-community/gpt2-medium-indonesian", | |
| "--model_type=gpt2", | |
| "--config_name=/home/cahya/Work/flax-community/gpt2-medium-indonesian", | |
| "--tokenizer_name=/home/cahya/Work/flax-community/gpt2-medium-indonesian", | |
| "--dataset_name=oscar", | |
| "--dataset_config_name=unshuffled_deduplicated_id", | |
| "--do_train", | |
| "--do_eval", | |
| "--block_size=512", | |
| "--per_device_train_batch_size=24", | |
| "--per_device_eval_batch_size=24", | |
| "--learning_rate=0.0024", | |
| "--warmup_steps=1000", | |
| "--adam_beta1=0.9", | |
| "--adam_beta2=0.98", | |
| "--weight_decay=0.01", | |
| "--overwrite_output_dir", | |
| "--num_train_epochs=20", | |
| "--dataloader_num_workers=64", | |
| "--preprocessing_num_workers=64", | |
| "--save_steps=10", | |
| "--eval_steps=10", | |
| "--max_train_samples=10000", | |
| "--max_eval_samples=1000", | |
| "--push_to_hub" | |
| ], | |
| "state": "running", | |
| "program": "./run_clm_flax.py", | |
| "codePath": "run_clm_flax.py", | |
| "git": { | |
| "remote": "https://huggingface.co/flax-community/gpt2-medium-indonesian", | |
| "commit": "6f9afb3df1b5b586dcf274b6e6e9cbae1deff345" | |
| }, | |
| "email": "cahya.wirawan@gmail.com", | |
| "root": "/home/cahya/Work/flax-community/gpt2-medium-indonesian", | |
| "host": "t1v-n-528d9406-w-0", | |
| "username": "cahya", | |
| "executable": "/home/cahya/miniconda3/envs/jax/bin/python" | |
| } | |