End of training
Browse files- README.md +1 -1
- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
|
|
| 43 |
- total_train_batch_size: 16
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- training_steps:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
| 43 |
- total_train_batch_size: 16
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- training_steps: 200
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
adapter_config.json
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
-
"lora_alpha":
|
| 14 |
"lora_dropout": 0.1,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
|
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
"lora_dropout": 0.1,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268453016
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:475bdda9aec8cfbfc993c752fa698e5dbe22b28f8173aac106b6df66e0da20ae
|
| 3 |
size 268453016
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac76855c263618cef0e263a0c124d9ddc7063f1656cefb5c835dbe3155a617b9
|
| 3 |
size 5432
|