Model save
Browse files
README.md
CHANGED
@@ -38,10 +38,10 @@ The following hyperparameters were used during training:
|
|
38 |
- eval_batch_size: 16
|
39 |
- seed: 42
|
40 |
- distributed_type: multi-GPU
|
41 |
-
- num_devices:
|
42 |
- gradient_accumulation_steps: 4
|
43 |
-
- total_train_batch_size:
|
44 |
-
- total_eval_batch_size:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: cosine
|
47 |
- num_epochs: 1
|
|
|
38 |
- eval_batch_size: 16
|
39 |
- seed: 42
|
40 |
- distributed_type: multi-GPU
|
41 |
+
- num_devices: 4
|
42 |
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 128
|
44 |
+
- total_eval_batch_size: 64
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: cosine
|
47 |
- num_epochs: 1
|
adapter_config.json
CHANGED
@@ -16,9 +16,9 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
"q_proj",
|
21 |
-
"k_proj",
|
22 |
"o_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"v_proj",
|
21 |
"q_proj",
|
|
|
22 |
"o_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
runs/Feb01_23-53-05_r2d2-devbox-lcd4w/events.out.tfevents.1738454128.r2d2-devbox-lcd4w.1270.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aadaf05ca4fe7168f6afc16c98e993cc6e4ac6d490a1355d8aed3ab7740f32b1
|
3 |
+
size 4619
|
step_0/README.md
CHANGED
@@ -203,18 +203,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
203 |
### Framework versions
|
204 |
|
205 |
|
206 |
-
- PEFT 0.6.1
|
207 |
-
## Training procedure
|
208 |
-
|
209 |
-
|
210 |
-
### Framework versions
|
211 |
-
|
212 |
-
|
213 |
-
- PEFT 0.6.1
|
214 |
-
## Training procedure
|
215 |
-
|
216 |
-
|
217 |
-
### Framework versions
|
218 |
-
|
219 |
-
|
220 |
- PEFT 0.6.1
|
|
|
203 |
### Framework versions
|
204 |
|
205 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
- PEFT 0.6.1
|
step_0/adapter_config.json
CHANGED
@@ -16,9 +16,9 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
"q_proj",
|
21 |
-
"k_proj",
|
22 |
"o_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"v_proj",
|
21 |
"q_proj",
|
|
|
22 |
"o_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
step_0/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3475e0f2e68ba04602c72e3234d42f97918aa20e3608d82b33595979ce095a23
|
3 |
size 5816
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3475e0f2e68ba04602c72e3234d42f97918aa20e3608d82b33595979ce095a23
|
3 |
size 5816
|