End of training
Browse files- README.md +10 -10
- adapter_config.json +2 -2
- adapter_model.bin +2 -2
- adapter_model.safetensors +2 -2
- runs/Nov04_22-39-20_3e84e73cd1f0/events.out.tfevents.1699137584.3e84e73cd1f0.14417.0 +3 -0
- runs/Nov04_22-50-37_3e84e73cd1f0/events.out.tfevents.1699138240.3e84e73cd1f0.14417.1 +3 -0
- tokenizer.json +1 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 2.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -48,15 +48,15 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| 2.
|
52 |
-
| 2.
|
53 |
-
| 2.
|
54 |
-
| 2.
|
55 |
-
| 2.
|
56 |
-
| 2.
|
57 |
-
| 2.
|
58 |
-
| 2.
|
59 |
-
| 2.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.6005
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 2.5714 | 0.1 | 200 | 2.6784 |
|
52 |
+
| 2.5921 | 0.2 | 400 | 2.6719 |
|
53 |
+
| 2.5493 | 0.3 | 600 | 2.6583 |
|
54 |
+
| 2.602 | 0.4 | 800 | 2.6390 |
|
55 |
+
| 2.5574 | 0.5 | 1000 | 2.6373 |
|
56 |
+
| 2.5859 | 0.6 | 1200 | 2.6265 |
|
57 |
+
| 2.552 | 0.7 | 1400 | 2.6172 |
|
58 |
+
| 2.5306 | 0.8 | 1600 | 2.6099 |
|
59 |
+
| 2.5827 | 0.9 | 1800 | 2.6005 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -8,11 +8,11 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
-
"lora_alpha":
|
12 |
"lora_dropout": 0.05,
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
-
"r":
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
"lora_dropout": 0.05,
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
adapter_model.bin
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 sha256:526069d6801c5beaf27f157493f6e01cee94ac32615669415ffc6956d03c057e
|
3 |
+
size 12599806
|
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:fef3ec3f30e9d9b500ad2ea7335e917c1f098aa0d652d803a3d36eb61beb9f77
|
3 |
+
size 12588752
|
runs/Nov04_22-39-20_3e84e73cd1f0/events.out.tfevents.1699137584.3e84e73cd1f0.14417.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cea43b0f3a988d9a11fd7065499f1f07a6fe66f70c52fbf314ff8356d8774a61
|
3 |
+
size 6223
|
runs/Nov04_22-50-37_3e84e73cd1f0/events.out.tfevents.1699138240.3e84e73cd1f0.14417.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d53e012fc96978f33ba2f3c486bf4a542bded983026598bfe339e6f17c25b9f
|
3 |
+
size 13341
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 1024,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a69eac68f90d9ff24f28e26e0aa5e233f559abc076ee8cf115802a3bf058799d
|
3 |
size 4600
|