jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
Browse files- README.md +2 -0
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -38,6 +38,8 @@ The following hyperparameters were used during training:
|
|
| 38 |
- train_batch_size: 4
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
|
|
|
|
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 3.0
|
|
|
|
| 38 |
- train_batch_size: 4
|
| 39 |
- eval_batch_size: 4
|
| 40 |
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 32
|
| 42 |
+
- total_train_batch_size: 128
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- num_epochs: 3.0
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4988025760
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146cf8bcbc844ff8f755edf876db832278d6470e2bdc77b2e208726d14c5b0c5
|
| 3 |
size 4988025760
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 240691728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e92fdfabf70535e60ca8cce06a0435494081ee28599ea6ea8153d43bcd8a17bf
|
| 3 |
size 240691728
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aeeaeae07abb3b600721fcff524b926967b4d76b3ab572ce2efe1ab80fb1b7b
|
| 3 |
size 5944
|