DeepDream2045
commited on
End of training
Browse files- README.md +2 -2
- adapter_config.json +2 -2
- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -105,7 +105,7 @@ xformers_attention: true
|
|
105 |
|
106 |
This model is a fine-tuned version of [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) on the None dataset.
|
107 |
It achieves the following results on the evaluation set:
|
108 |
-
- Loss: 1.
|
109 |
|
110 |
## Model description
|
111 |
|
@@ -143,7 +143,7 @@ The following hyperparameters were used during training:
|
|
143 |
| Training Loss | Epoch | Step | Validation Loss |
|
144 |
|:-------------:|:------:|:----:|:---------------:|
|
145 |
| 1.2924 | 0.1019 | 1 | 1.4097 |
|
146 |
-
| 0.
|
147 |
|
148 |
|
149 |
### Framework versions
|
|
|
105 |
|
106 |
This model is a fine-tuned version of [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b) on the None dataset.
|
107 |
It achieves the following results on the evaluation set:
|
108 |
+
- Loss: 1.0479
|
109 |
|
110 |
## Model description
|
111 |
|
|
|
143 |
| Training Loss | Epoch | Step | Validation Loss |
|
144 |
|:-------------:|:------:|:----:|:---------------:|
|
145 |
| 1.2924 | 0.1019 | 1 | 1.4097 |
|
146 |
+
| 0.954 | 2.6369 | 25 | 1.0479 |
|
147 |
|
148 |
|
149 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -21,12 +21,12 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"up_proj",
|
24 |
-
"gate_proj",
|
25 |
"v_proj",
|
26 |
"down_proj",
|
27 |
"o_proj",
|
28 |
"q_proj",
|
29 |
-
"k_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"up_proj",
|
|
|
24 |
"v_proj",
|
25 |
"down_proj",
|
26 |
"o_proj",
|
27 |
"q_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_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 203538938
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:282ec3653226e6c810c19bcb85382ed98528740029944eaa1b81bd5db3928b9f
|
3 |
size 203538938
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 203456160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00f9538b271e8d8961813afd5ab30b65fd44804ac0d2fd5fc611c77eb726d97
|
3 |
size 203456160
|
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 sha256:11310abb03160086896271409f285f645e098cc1d2c620a9c8e344ab93359699
|
3 |
size 6776
|