| .. |
|
context_numbers_10.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_32.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_32_only.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_64.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_64_only.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_128.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_128_only.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_256.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_256_only.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_debug.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
context_numbers_easy.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
default.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
fw_qa.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
fw_qa_ctx_qa.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
fw_qa_large_ctx_pwc_hotpot.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
fw_qa_large_ctx_pwc_hotpot_squad.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
fw_qa_pwc_hotpot.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
fw_qa_tiny.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
gsm8k.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
hotpot_qa.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
math_and_code.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
openmathintx.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
pretrain_all.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
pretrain_all_2.yaml
|
add per rank latent query + per layer hyper head
|
2025-04-19 07:03:11 +00:00 |
|
pretrain_all_xl.yaml
|
fw_qa_xl + modernbert
|
2025-02-14 14:59:25 +00:00 |
|
pretrain_all_xl_3.yaml
|
allow streaming data
|
2025-05-09 10:59:08 +00:00 |
|
pretrain_all_xl_3_medium.yaml
|
medium fw qa 3 + fallback to manual cache dataset
|
2025-05-10 15:31:08 +00:00 |
|
pretrain_all_xl_3_mini.yaml
|
medium fw qa 3 + fallback to manual cache dataset
|
2025-05-10 15:31:08 +00:00 |
|
pretrain_all_xl_and_sum.yaml
|
add booksum and gov_report
|
2025-02-18 10:43:02 +00:00 |
|
pwc.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
pwc_and_ctx_numbers_256.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |
|
pwc_hotpot_qa.yaml
|
default warmup + decay
|
2025-01-28 21:36:19 +00:00 |