Skip to content

Actions: huggingface/trl

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
1,984 workflow run results
1,984 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

DPO models generate multiple / corrupted responses Benchmark on Comment #987: Issue comment #1025 (comment) created by Devy99
November 28, 2023 21:12 3s
November 28, 2023 21:12 3s
Update utils.py Tests #2212: Pull request #1012 synchronize by ZihanWang314
November 28, 2023 18:36 8m 48s ZihanWang314:patch-1
ZihanWang314:patch-1
November 28, 2023 18:36 8m 48s
Update utils.py Build PR Documentation #1793: Pull request #1012 synchronize by ZihanWang314
November 28, 2023 18:36 3m 34s ZihanWang314:patch-1
ZihanWang314:patch-1
November 28, 2023 18:36 3m 34s
Stale Bot Stale Bot #161: Scheduled
November 28, 2023 15:04 1m 2s main
main
November 28, 2023 15:04 1m 2s
Cleanup Cache Cleanup Cache #247: Scheduled
November 28, 2023 00:03 15s main
main
November 28, 2023 00:03 15s
How to load the model and the checkpoint after trained the model? Benchmark on Comment #986: Issue comment #674 (comment) created by louieworth
November 27, 2023 21:34 3s
November 27, 2023 21:34 3s
Benchmark on Comment Benchmark on Comment #985: created by wenlai-lavine
November 27, 2023 20:40 2s
November 27, 2023 20:40 2s
EOS token processing for multi-turn DPO Benchmark on Comment #984: Issue comment #741 (comment) created by natolambert
November 27, 2023 16:36 4s
November 27, 2023 16:36 4s
IPO loss resulting in NaN Benchmark on Comment #983: Issue comment #1033 (comment) created by orendar
November 27, 2023 16:09 4s
November 27, 2023 16:09 4s
Upload PR Documentation Upload PR Documentation #983: completed by vwxyzjn
November 27, 2023 15:29 25s
November 27, 2023 15:29 25s
Fixes reward and text gathering in distributed training Build PR Documentation #1792: Pull request #850 synchronize by vwxyzjn
November 27, 2023 15:26 3m 33s fix-reward-gather
fix-reward-gather
November 27, 2023 15:26 3m 33s
Fixes reward and text gathering in distributed training Tests #2211: Pull request #850 synchronize by vwxyzjn
November 27, 2023 15:26 5m 1s fix-reward-gather
fix-reward-gather
November 27, 2023 15:26 5m 1s
[WIP] Reward ranked finetuning (RAFT) and Reinforced Self-Training (ReST) Benchmark on Comment #982: Issue comment #704 (comment) created by lvwerra
November 27, 2023 15:26 2s
November 27, 2023 15:26 2s
Is it possible to use AutoModelForCausalLMWithValueHead without merging adapters first? Benchmark on Comment #981: Issue comment #1036 (comment) created by lvwerra
November 27, 2023 15:21 3s
November 27, 2023 15:21 3s
Upload PR Documentation Upload PR Documentation #982: completed by vwxyzjn
November 27, 2023 15:20 3s
November 27, 2023 15:20 3s
Fixes reward and text gathering in distributed training Build PR Documentation #1791: Pull request #850 synchronize by vwxyzjn
November 27, 2023 15:17 3m 5s fix-reward-gather
fix-reward-gather
November 27, 2023 15:17 3m 5s
Fixes reward and text gathering in distributed training Tests #2210: Pull request #850 synchronize by vwxyzjn
November 27, 2023 15:17 36s fix-reward-gather
fix-reward-gather
November 27, 2023 15:17 36s
DeepSpeed Zero3 dpo accured embedding weight error Benchmark on Comment #980: Issue comment #669 (comment) created by lvwerra
November 27, 2023 15:06 3s
November 27, 2023 15:06 3s
Stale Bot Stale Bot #160: Scheduled
November 27, 2023 15:04 1m 8s main
main
November 27, 2023 15:04 1m 8s
IPO loss resulting in NaN Benchmark on Comment #979: Issue comment #1033 (comment) created by lvwerra
November 27, 2023 14:59 3s
November 27, 2023 14:59 3s
Upload PR Documentation Upload PR Documentation #981: completed by vwxyzjn
November 27, 2023 14:59 25s
November 27, 2023 14:59 25s
Fixes reward and text gathering in distributed training Build PR Documentation #1790: Pull request #850 synchronize by vwxyzjn
November 27, 2023 14:55 3m 40s fix-reward-gather
fix-reward-gather
November 27, 2023 14:55 3m 40s
Fixes reward and text gathering in distributed training Tests #2209: Pull request #850 synchronize by vwxyzjn
November 27, 2023 14:55 37s fix-reward-gather
fix-reward-gather
November 27, 2023 14:55 37s
DPO models generate multiple / corrupted responses Benchmark on Comment #978: Issue comment #1025 (comment) created by Ricardokevins
November 27, 2023 04:57 2s
November 27, 2023 04:57 2s
DPO trainer with deepspped offload cpu config cause error: AssertionError: CPUAdam param is on cuda:0 and must be 'cpu', make sure you enabled 'offload_optimizer': 'cpu' in your ZeRO config. Benchmark on Comment #977: Issue comment #955 (comment) created by ttzHome
November 27, 2023 03:21 2s
November 27, 2023 03:21 2s