zhangdah/gemma-2b-finetune-test
Browse files
README.md
CHANGED
|
@@ -35,15 +35,15 @@ More information needed
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
-
- train_batch_size:
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
| 41 |
- gradient_accumulation_steps: 4
|
| 42 |
-
- total_train_batch_size:
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
| 41 |
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 16
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
+
- num_epochs: 10
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4911635192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f6b4d725b90a3f1269c9a69c9de8ec4208bd4789f7970a6a2e051218ea2956f
|
| 3 |
size 4911635192
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4978830584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f09c98c4416cfa32a951126a88c83f79adf21766fb381ed199fa282a143e36b
|
| 3 |
size 4978830584
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134242760
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:051f4ded304a2adf351ca7339ac3547d334e48221dddbdf3c4c19a05e922ac86
|
| 3 |
size 134242760
|
runs/Sep04_01-45-56_7678ee64f446/events.out.tfevents.1725414361.7678ee64f446.1409.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ece56e8ef8fcfb036be4f63a31894d916093620cded42d4f72af746bd7ec141
|
| 3 |
+
size 5511
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c026dd2e8b6dd5434a16112353ee4e776482e9c193a844c940ebe96510e7f24a
|
| 3 |
size 5368
|