bif02/operons
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -52,15 +52,15 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
- PEFT 0.12.0
|
63 |
-
- Transformers 4.44.
|
64 |
- Pytorch 2.4.0+cu121
|
65 |
- Datasets 2.21.0
|
66 |
- Tokenizers 0.19.1
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.2856
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.4054 | 1.0 | 76 | 0.3959 |
|
56 |
+
| 0.2973 | 2.0 | 152 | 0.3042 |
|
57 |
+
| 0.2746 | 3.0 | 228 | 0.2856 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
- PEFT 0.12.0
|
63 |
+
- Transformers 4.44.2
|
64 |
- Pytorch 2.4.0+cu121
|
65 |
- Datasets 2.21.0
|
66 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
23 |
"gate_proj",
|
24 |
"down_proj",
|
25 |
-
"o_proj",
|
26 |
-
"k_proj",
|
27 |
"q_proj",
|
28 |
-
"
|
29 |
-
"v_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
"gate_proj",
|
27 |
"down_proj",
|
|
|
|
|
28 |
"q_proj",
|
29 |
+
"k_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 35668592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bdb8fe5e3c5bc21eaa2daeef7713c2669fa1f542a5c776fe31d6f91a96c6c84
|
3 |
size 35668592
|
runs/Aug23_09-30-47_bb9eb7dac2b6/events.out.tfevents.1724405623.bb9eb7dac2b6.3964.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89c4948b65ca5b475aa766fde0bdf5d0aa6e7e750551cff19826e42a279fdc53
|
3 |
+
size 14299
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a72254ff442a085ab0d5bbfe26177cb8bcc342e246342de3b12e90b384ef01b
|
3 |
size 5432
|