End of training
Browse files
README.md
CHANGED
@@ -34,8 +34,8 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0002
|
37 |
-
- train_batch_size:
|
38 |
-
- eval_batch_size:
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: cosine
|
@@ -49,6 +49,6 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
- PEFT 0.8.2
|
51 |
- Transformers 4.37.2
|
52 |
-
- Pytorch 2.
|
53 |
-
- Datasets 2.19.
|
54 |
- Tokenizers 0.15.2
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0002
|
37 |
+
- train_batch_size: 16
|
38 |
+
- eval_batch_size: 32
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: cosine
|
|
|
49 |
|
50 |
- PEFT 0.8.2
|
51 |
- Transformers 4.37.2
|
52 |
+
- Pytorch 2.3.0+cu121
|
53 |
+
- Datasets 2.19.1
|
54 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_rslora": false
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"gate_up_proj",
|
23 |
+
"o_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cef7d3db8482fa1656c71ce896de4d706f3876e6907dcbe7f0a285d9f6209d2b
|
3 |
+
size 26233776
|
runs/May09_13-11-44_cbnu-DGX-Station/events.out.tfevents.1715227914.cbnu-DGX-Station.2152000.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75f9e03d905d443b0540d9b8bf6cc5a81aed7fc6f535935dbce7ba31527f63a
|
3 |
+
size 7024
|
runs/May09_14-02-26_cbnu-DGX-Station/events.out.tfevents.1715230953.cbnu-DGX-Station.2158130.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:303a0483f10d388049a5702598b02dba3b1d3181913bde2208189f7cdb2adc87
|
3 |
+
size 7024
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7098eb921aee8fcd4a260237cdf3708ecc0178eeccf10da63a41b374abeb24d
|
3 |
size 4728
|