End of training
Browse files- README.md +3 -3
- adapter_config.json +3 -3
- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -102,7 +102,7 @@ xformers_attention: false
|
|
102 |
|
103 |
This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
|
104 |
It achieves the following results on the evaluation set:
|
105 |
-
- Loss: 10.
|
106 |
|
107 |
## Model description
|
108 |
|
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
|
|
137 |
| Training Loss | Epoch | Step | Validation Loss |
|
138 |
|:-------------:|:------:|:----:|:---------------:|
|
139 |
| 10.3767 | 0.0006 | 1 | 10.3780 |
|
140 |
-
| 10.
|
141 |
| 10.3798 | 0.0216 | 38 | 10.3769 |
|
142 |
-
| 10.
|
143 |
|
144 |
|
145 |
### Framework versions
|
|
|
102 |
|
103 |
This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
|
104 |
It achieves the following results on the evaluation set:
|
105 |
+
- Loss: 10.3766
|
106 |
|
107 |
## Model description
|
108 |
|
|
|
137 |
| Training Loss | Epoch | Step | Validation Loss |
|
138 |
|:-------------:|:------:|:----:|:---------------:|
|
139 |
| 10.3767 | 0.0006 | 1 | 10.3780 |
|
140 |
+
| 10.3794 | 0.0108 | 19 | 10.3775 |
|
141 |
| 10.3798 | 0.0216 | 38 | 10.3769 |
|
142 |
+
| 10.3798 | 0.0324 | 57 | 10.3766 |
|
143 |
|
144 |
|
145 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"k_proj",
|
|
|
24 |
"v_proj",
|
25 |
-
"gate_proj",
|
26 |
"up_proj",
|
27 |
-
"down_proj",
|
28 |
-
"o_proj",
|
29 |
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"o_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
"v_proj",
|
|
|
28 |
"up_proj",
|
|
|
|
|
29 |
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33666
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068a0f1596e4bfb2d70c8e06fda526087456623429256b24bed795bc18966baf
|
3 |
size 33666
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ccbe4a0c998eb835a47fbe6207f2a22426d028688fa337dbf66818cc9533b8c
|
3 |
size 27024
|
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 sha256:517a25a9599c323c2bf30994b724f846f84d5599c9321c0962275c2f1e4f6021
|
3 |
size 6776
|