Model save
Browse files
README.md
CHANGED
@@ -36,11 +36,11 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0002
|
39 |
-
- train_batch_size:
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 4
|
43 |
-
- total_train_batch_size:
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_steps: 20
|
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 16
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 64
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_steps: 20
|
model_fold_0_batch0/adapter_config.json
CHANGED
@@ -40,8 +40,8 @@
|
|
40 |
"rank_pattern": {},
|
41 |
"revision": null,
|
42 |
"target_modules": [
|
43 |
-
"v_proj",
|
44 |
"q_proj",
|
|
|
45 |
"k_proj"
|
46 |
],
|
47 |
"task_type": "SEQ_CLS",
|
|
|
40 |
"rank_pattern": {},
|
41 |
"revision": null,
|
42 |
"target_modules": [
|
|
|
43 |
"q_proj",
|
44 |
+
"v_proj",
|
45 |
"k_proj"
|
46 |
],
|
47 |
"task_type": "SEQ_CLS",
|
model_fold_0_batch0/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4780504
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1be428f0b31a3975a1449bdd88293a28c3058a9fd4c06e3a71f730300c3f8572
|
3 |
size 4780504
|
model_fold_0_batch0/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdbefeb2bdec2011894dc6af7b992e7a7a555c67bc61e6df035bb68e9a5a4817
|
3 |
size 5496
|