rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_10_of_10
1B
•
Updated
Rosie Zhao
rosieyzh
·
AI & ML interests
theory of machine learning, deep learning
Recent Activity
updated
a model
about 1 hour ago
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_10_of_10
published
a model
about 1 hour ago
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_10_of_10
updated
a model
about 1 hour ago
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_9_of_10
Organizations
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_9_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_8_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_7_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_6_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_5_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_4_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_3_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_2_of_10
1B
•
Updated
rosieyzh/rlvr_llama1_warmstart_rouge_xsum_rbz_64_ckpt_1_of_10
1B
•
Updated
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_64_ckpt_5_of_5
1B
•
Updated
•
11
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_64_ckpt_4_of_5
1B
•
Updated
•
8
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_64_ckpt_3_of_5
1B
•
Updated
•
8
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_64_ckpt_2_of_5
1B
•
Updated
•
7
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_64_ckpt_1_of_5
1B
•
Updated
•
8
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
1B
•
Updated
•
9
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
1B
•
Updated
•
11
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
1B
•
Updated
•
12
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_128_ckpt_2_of_5
1B
•
Updated
•
4
rosieyzh/sft_llama1_xsum_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
1B
•
Updated
•
6
rosieyzh/sft_llama1_xsum_lr_1e-5_constant_bsz_64_one_epoch_ckpt_2_of_2
1B
•
Updated
•
21
rosieyzh/sft_llama1_xsum_lr_1e-5_constant_bsz_64_one_epoch_ckpt_1_of_2
1B
•
Updated
•
9
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_5_of_5
2B
•
Updated
•
26
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_4_of_5
2B
•
Updated
•
26
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_3_of_5
2B
•
Updated
•
27
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_2_of_5
2B
•
Updated
•
26
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_128_ckpt_1_of_5
2B
•
Updated
•
31
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_64_ckpt_5_of_5
2B
•
Updated
•
25
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_64_ckpt_4_of_5
2B
•
Updated
•
23
rosieyzh/sft_qwen15_swallow_lr_1e-5_cosine_bsz_64_ckpt_3_of_5
2B
•
Updated
•
28