jwongTensora
commited on
End of training
Browse files- README.md +2 -2
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -39,7 +39,7 @@ early_stopping_patience: null
|
|
39 |
eval_max_new_tokens: 128
|
40 |
eval_table_size: null
|
41 |
evals_per_epoch: 4
|
42 |
-
flash_attention:
|
43 |
fp16: null
|
44 |
fsdp: null
|
45 |
fsdp_config: null
|
@@ -82,7 +82,7 @@ train_on_inputs: false
|
|
82 |
trust_remote_code: true
|
83 |
val_set_size: 0.05
|
84 |
wandb_entity: null
|
85 |
-
wandb_mode:
|
86 |
wandb_name: 00000000-0000-0000-0000-000000000000
|
87 |
wandb_project: Gradients-On-Demand
|
88 |
wandb_run: your_name
|
|
|
39 |
eval_max_new_tokens: 128
|
40 |
eval_table_size: null
|
41 |
evals_per_epoch: 4
|
42 |
+
flash_attention: true
|
43 |
fp16: null
|
44 |
fsdp: null
|
45 |
fsdp_config: null
|
|
|
82 |
trust_remote_code: true
|
83 |
val_set_size: 0.05
|
84 |
wandb_entity: null
|
85 |
+
wandb_mode: disabled
|
86 |
wandb_name: 00000000-0000-0000-0000-000000000000
|
87 |
wandb_project: Gradients-On-Demand
|
88 |
wandb_run: your_name
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bad72ac69a8ea0e3f6d1dd6e9d0627b722cd79446e99703c751c2aaad24d35c
|
3 |
size 21378
|