Roselia-penguin
commited on
Commit
•
01b2bc2
1
Parent(s):
3932839
Update README.md
Browse files
README.md
CHANGED
@@ -123,7 +123,7 @@ llamafactory-cli train \
|
|
123 |
--optim adamw_torch \
|
124 |
--packing False \
|
125 |
--report_to none \
|
126 |
-
--output_dir saves/Qwen1.5-7B-Chat/lora/
|
127 |
--fp16 True \
|
128 |
--plot_loss True \
|
129 |
--ddp_timeout 180000000 \
|
@@ -133,6 +133,7 @@ llamafactory-cli train \
|
|
133 |
--lora_dropout 0.05 \
|
134 |
--lora_target all \
|
135 |
|
|
|
136 |
#### Speeds, Sizes, Times [optional]
|
137 |
|
138 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
|
|
123 |
--optim adamw_torch \
|
124 |
--packing False \
|
125 |
--report_to none \
|
126 |
+
--output_dir saves/Qwen1.5-7B-Chat/lora/4-bit_Qwen1.5-7B-Chat \
|
127 |
--fp16 True \
|
128 |
--plot_loss True \
|
129 |
--ddp_timeout 180000000 \
|
|
|
133 |
--lora_dropout 0.05 \
|
134 |
--lora_target all \
|
135 |
|
136 |
+
|
137 |
#### Speeds, Sizes, Times [optional]
|
138 |
|
139 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|