End of training
Browse files- README.md +2 -2
- adapter_config.json +4 -4
- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -103,7 +103,7 @@ xformers_attention: true
|
|
103 |
|
104 |
This model is a fine-tuned version of [unsloth/codellama-7b](https://huggingface.co/unsloth/codellama-7b) on the None dataset.
|
105 |
It achieves the following results on the evaluation set:
|
106 |
-
- Loss: 0.
|
107 |
|
108 |
## Model description
|
109 |
|
@@ -141,7 +141,7 @@ The following hyperparameters were used during training:
|
|
141 |
| Training Loss | Epoch | Step | Validation Loss |
|
142 |
|:-------------:|:------:|:----:|:---------------:|
|
143 |
| 6.1391 | 0.0842 | 1 | 6.0623 |
|
144 |
-
| 0.
|
145 |
|
146 |
|
147 |
### Framework versions
|
|
|
103 |
|
104 |
This model is a fine-tuned version of [unsloth/codellama-7b](https://huggingface.co/unsloth/codellama-7b) on the None dataset.
|
105 |
It achieves the following results on the evaluation set:
|
106 |
+
- Loss: 0.2695
|
107 |
|
108 |
## Model description
|
109 |
|
|
|
141 |
| Training Loss | Epoch | Step | Validation Loss |
|
142 |
|:-------------:|:------:|:----:|:---------------:|
|
143 |
| 6.1391 | 0.0842 | 1 | 6.0623 |
|
144 |
+
| 0.4549 | 2.1053 | 25 | 0.2695 |
|
145 |
|
146 |
|
147 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"down_proj",
|
24 |
"up_proj",
|
25 |
-
"
|
26 |
"gate_proj",
|
|
|
27 |
"v_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"up_proj",
|
24 |
+
"q_proj",
|
25 |
"gate_proj",
|
26 |
+
"down_proj",
|
27 |
"v_proj",
|
28 |
+
"k_proj",
|
29 |
+
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319977674
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2bbf1dbfe936f142d115c51d2af7fcb378ec8480a479421f808570dc4c606b3
|
3 |
size 319977674
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ca0b619f50815c75766eba262bdd3856924f972e6a62ebecac6a1d1ee351dcd
|
3 |
size 319876032
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62fe8c0855098ea055d918c702f52c1e692bb20ceaf0bb7577a4d6f246e27023
|
3 |
size 6776
|