Skip to content

Actions: jshuadvd/LongRoPE

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
147 workflow runs
147 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Update the training notebook with the latest training updates Sync with Hugging Face #122: Commit 5189c33 pushed by jshuadvd
July 15, 2024 04:11 32s master
master
July 15, 2024 04:11 32s
Update the training notebook with the latest training updates Sync with Hugging Face #121: Commit 324b811 pushed by jshuadvd
July 15, 2024 04:09 19s master
master
July 15, 2024 04:09 19s
Update the training notebook with the latest training updates Sync with Hugging Face #120: Commit 9847267 pushed by jshuadvd
July 15, 2024 04:08 18s master
master
July 15, 2024 04:08 18s
Log GPU memory usage Sync with Hugging Face #119: Commit bd0ede3 pushed by jshuadvd
July 14, 2024 05:03 20s master
master
July 14, 2024 05:03 20s
Update preprocess_data with tdqm to vizualize processing Sync with Hugging Face #118: Commit cba5999 pushed by jshuadvd
July 14, 2024 04:56 26s master
master
July 14, 2024 04:56 26s
Add gradient clipping Sync with Hugging Face #117: Commit 440f184 pushed by jshuadvd
July 13, 2024 05:46 17s master
master
July 13, 2024 05:46 17s
Add StreamingDataset class for better handling of the long sequences Sync with Hugging Face #116: Commit f07081c pushed by jshuadvd
July 13, 2024 05:44 20s master
master
July 13, 2024 05:44 20s
remove duplicate code Sync with Hugging Face #115: Commit 506daf2 pushed by jshuadvd
July 13, 2024 04:57 17s master
master
July 13, 2024 04:57 17s
Update notebook training code Sync with Hugging Face #114: Commit 013cf7a pushed by jshuadvd
July 12, 2024 05:51 16s master
master
July 12, 2024 05:51 16s
Update notebook training code Sync with Hugging Face #113: Commit 3c67e6f pushed by jshuadvd
July 12, 2024 05:50 18s master
master
July 12, 2024 05:50 18s
Update notebook training code Sync with Hugging Face #112: Commit 809d7a5 pushed by jshuadvd
July 12, 2024 05:48 22s master
master
July 12, 2024 05:48 22s
Implement a caching mechanism for tokenized sequences Sync with Hugging Face #111: Commit 1c1a00b pushed by jshuadvd
July 11, 2024 06:59 15s master
master
July 11, 2024 06:59 15s
Implement a caching mechanism for tokenized sequences Sync with Hugging Face #110: Commit 287957e pushed by jshuadvd
July 11, 2024 06:58 14s master
master
July 11, 2024 06:58 14s
Implement a caching mechanism for tokenized sequences Sync with Hugging Face #109: Commit 939aa76 pushed by jshuadvd
July 11, 2024 06:56 18s master
master
July 11, 2024 06:56 18s
Save the final model Sync with Hugging Face #108: Commit 99c846b pushed by jshuadvd
July 10, 2024 05:28 14s master
master
July 10, 2024 05:28 14s
Add a simple validation step after short context recovery Sync with Hugging Face #107: Commit 7f2c9ef pushed by jshuadvd
July 10, 2024 05:27 14s master
master
July 10, 2024 05:27 14s
Update the progressive training and the finetuning for different leng… Sync with Hugging Face #106: Commit 118c02e pushed by jshuadvd
July 9, 2024 06:08 19s master
master
July 9, 2024 06:08 19s
Update the remainig logs and checks for the global_step Sync with Hugging Face #105: Commit 96ad654 pushed by jshuadvd
July 9, 2024 06:03 21s master
master
July 9, 2024 06:03 21s
updated logger to include global_step Sync with Hugging Face #104: Commit 947bd63 pushed by jshuadvd
July 9, 2024 06:02 24s master
master
July 9, 2024 06:02 24s
Added global_step to check the steps we are at Sync with Hugging Face #103: Commit 64054e5 pushed by jshuadvd
July 9, 2024 05:58 18s master
master
July 9, 2024 05:58 18s
Added max_steps parameter to set the maximum number of steps to train Sync with Hugging Face #102: Commit 6b32640 pushed by jshuadvd
July 9, 2024 05:41 20s master
master
July 9, 2024 05:41 20s
Refactor and clean up to keep the training more simplistic Sync with Hugging Face #101: Commit f2715ae pushed by jshuadvd
July 9, 2024 05:15 16s master
master
July 9, 2024 05:15 16s
Added a process_dataset function to well, process data Sync with Hugging Face #100: Commit 4b03d93 pushed by jshuadvd
July 9, 2024 04:06 17s master
master
July 9, 2024 04:06 17s
Add concatenate_datasets from huggingface as well as the outlines for… Sync with Hugging Face #99: Commit f885fc7 pushed by jshuadvd
July 8, 2024 05:07 17s master
master
July 8, 2024 05:07 17s
Remove eval_frequency as it is better to evaluate constantly Sync with Hugging Face #98: Commit f03ea61 pushed by jshuadvd
July 8, 2024 04:44 18s master
master
July 8, 2024 04:44 18s