Skip to content

Actions: huggingface/trl

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
2,456 workflow run results
2,456 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

How to prepare multi-turn dialogue dataset for dpo? Benchmark on Comment #1242: Issue comment #1115 (comment) created by lvwerra
December 21, 2023 15:28 2s
December 21, 2023 15:28 2s
Question on DPO's concatenated_forward Benchmark on Comment #1241: Issue comment #1113 (comment) created by lvwerra
December 21, 2023 15:27 2s
December 21, 2023 15:27 2s
Eval dataset issue in DPOTrainer when precompute_ref_log_probs=True and ref_model=None Benchmark on Comment #1240: Issue comment #1107 (comment) created by kashif
December 21, 2023 15:27 2s
December 21, 2023 15:27 2s
[Docs] Add unsloth optimizations in TRL's documentation Benchmark on Comment #1239: Issue comment #1119 (comment) created by danielhanchen
December 21, 2023 15:25 3s
December 21, 2023 15:25 3s
Reference model alignment with the current policy Benchmark on Comment #1238: Issue comment #1112 (comment) created by lvwerra
December 21, 2023 15:25 3s
December 21, 2023 15:25 3s
QLoRA memory requirement with 3B model loads GPU with 10GB of memory with 4bit quantization Benchmark on Comment #1237: Issue comment #1111 (comment) created by lvwerra
December 21, 2023 15:23 3s
December 21, 2023 15:23 3s
SFTTrainer encounters error with OPT finetuning (int8 + LoRA) Benchmark on Comment #1236: Issue comment #1109 (comment) created by lvwerra
December 21, 2023 15:22 2s
December 21, 2023 15:22 2s
Does the hidden states need detached when training a LLama ? Benchmark on Comment #1235: Issue comment #1108 (comment) created by lvwerra
December 21, 2023 15:21 3s
December 21, 2023 15:21 3s
Eval dataset issue in DPOTrainer when precompute_ref_log_probs=True and ref_model=None Benchmark on Comment #1234: Issue comment #1107 (comment) created by lvwerra
December 21, 2023 15:18 3s
December 21, 2023 15:18 3s
Difference between RewardTrainer and DPOTrainer? when to use each over the other? Benchmark on Comment #1233: Issue comment #1106 (comment) created by lvwerra
December 21, 2023 15:15 2s
December 21, 2023 15:15 2s
PPO script hangs when logging to wandb in multi-gpu environments Benchmark on Comment #1232: Issue comment #1103 (comment) created by lvwerra
December 21, 2023 15:10 3s
December 21, 2023 15:10 3s
Stale Bot Stale Bot #184: Scheduled
December 21, 2023 15:04 1m 14s main
main
December 21, 2023 15:04 1m 14s
[DataCollatorForCompletionOnlyLM] Are the input_ids supposed to contain the labels? Benchmark on Comment #1231: Issue comment #632 (comment) created by lvwerra
December 21, 2023 15:00 3s
December 21, 2023 15:00 3s
Update description in setup.py (#1101) Build documentation #414: Commit 2aff709 pushed by lvwerra
December 21, 2023 14:35 3m 22s main
main
December 21, 2023 14:35 3m 22s
Update description in setup.py (#1101) Tests #2319: Commit 2aff709 pushed by lvwerra
December 21, 2023 14:35 8m 22s main
main
December 21, 2023 14:35 8m 22s
pages build and deployment pages-build-deployment #431: by lvwerra
December 21, 2023 14:35 49s main
main
December 21, 2023 14:35 49s
Add type hints to core.py Benchmark on Comment #1230: Issue comment #1097 (comment) created by zachschillaci27
December 21, 2023 14:27 2s
December 21, 2023 14:27 2s
Add type hints to core.py Build PR Documentation #1870: Pull request #1097 synchronize by zachschillaci27
December 21, 2023 14:27 3m 37s zachschillaci27:type-hint-core
zachschillaci27:type-hint-core
December 21, 2023 14:27 3m 37s
Add type hints to core.py Tests #2318: Pull request #1097 synchronize by zachschillaci27
December 21, 2023 14:27 29s zachschillaci27:type-hint-core
zachschillaci27:type-hint-core
December 21, 2023 14:27 29s
Add type hints to core.py Benchmark on Comment #1229: Issue comment #1097 (comment) created by HuggingFaceDocBuilderDev
December 21, 2023 14:21 2s
December 21, 2023 14:21 2s
Upload PR Documentation Upload PR Documentation #1046: completed by zachschillaci27
December 21, 2023 14:21 36s
December 21, 2023 14:21 36s
Add type hints to core.py Benchmark on Comment #1228: Issue comment #1097 (comment) created by lvwerra
December 21, 2023 14:20 3s
December 21, 2023 14:20 3s
PPOTrainer: Right way to generate text during inference ? Benchmark on Comment #1227: Issue comment #1093 (comment) created by lvwerra
December 21, 2023 14:12 2s
December 21, 2023 14:12 2s
Issue concerning log when using packing=True Benchmark on Comment #1226: Issue comment #1090 (comment) created by Forbu
December 21, 2023 14:11 2s
December 21, 2023 14:11 2s
Issue concerning log when using packing=True Benchmark on Comment #1225: Issue comment #1090 (comment) created by lvwerra
December 21, 2023 14:03 3s
December 21, 2023 14:03 3s