End of training
Browse files
README.md
CHANGED
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
|
|
41 |
- total_train_batch_size: 4
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
-
- training_steps:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
|
|
41 |
- total_train_batch_size: 4
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
+
- training_steps: 150
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM"
|
26 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4517152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c4014f7ba0213cc859d244f44accf8afded9a6c0d88b1348a19d7f498a3e02
|
3 |
size 4517152
|
runs/Dec08_04-19-50_58593d1e2e5d/events.out.tfevents.1702009198.58593d1e2e5d.43.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c100f140a8950c1d77902e0e59967f1a9e69643d94b8415a3aefa86816d598f
|
3 |
+
size 7427
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e405a6ebfd084c7a878869e7c8cbec5e728a48ea758a6e7576dbbe77d7c1b898
|
3 |
size 4219
|